Search

High-speed data communication is becoming essential for many applications, including satellite communication. The security algorithms associated with the communication of information are also required to have high-speed for coping up with the communication speed. Moreover, the Authenticated Encryption (AE) algorithms provide high-speed communication and security services include data encryption, authentication, and integrity. The AE algorithms are available with serial and parallel architectures; among them, the Galois Counter Mode (GCM) algorithm has a parallel architecture. The Synthetic Initialization Vector (SIV) mode in the AES-GCM-SIV algorithm provides the nonce misuse protection using the GCM algorithm. Besides, reduced data throughput is provided using the AES-GCM-SIV algorithm as compared to the AES-GCM algorithm. This work introduced a parallel algorithm with re-keying and randomization of the initialization vector for high data throughput, nonce misuse protection, and side-channel attack protection. The implementation of the proposed algorithm is performed on Field Programmable Gate Array (FPGA) and it’s compared with the FPGA implementations of AES-GCM, AES-GCM-SIV, and recently introduced algorithms. The optimization of the proposed algorithm and security analysis is presented for space application using different optimizations and a combination of optimizations.

The digital design methodologies are evolving with the increase of digital systems utilization in daily life. The Model Based Design (MBD) methodology provides a unique methodology for design and implementation of digital systems on Field Programmable Gate Array (FPGA). Recently, a lot of research effort has been put to exploit new methodologies for designing and prototyping of digital systems on FPGA. The FPGA hardware provides prototyping which provides means of verifying your design at an early stage of development cycle. This helps to evaluate design trade-offs by testing the design in real-time on hardware. Making prototypes is a common practice in research-oriented projects. However, it requires excess development time which increases time to market of the product. This paper illustrates the use of reconfigurable MBD for rapid prototyping of digital systems on Microsemi ACTEL FPGAs for improving the design-cycle and time-to-market of a product. The model is simulated to verify the functionality of the design at system-level and a high-level code is generated from the MBD toolset embedded in MATLAB for hardware implementation. Then, a High-Level Synthesis (HLS) is performed on the generated code which converts this high-level code into Verilog-HDL suitable for hardware implementation on FPGA. Hence, this work presents a methodology and its analysis for design of digital system using high-level synthesis on Microsemi ACTEL FPGA.

Over the past 60 years, satellite technology has demonstrated its usefulness successfully. However, this usefulness is at stake from a future point of view, due to the well-admitted orbital/space debris threat. This article thoroughly reviews all aspects of space debris issue including causes, amount and sizes of orbital debris, potential threats, counter-strategies with their latest status and related legal issues to highlight the criticality and urgency of the problem. This review elaborates the fact that despite all the worries and threats, the efforts to confront this challenge are considerably insufficient until today. This bitter reality demands for at-least curtailing the number of future launches to ensure the long-term sustainability of space, until the improvement in debris situation. However, contradictory to this necessity, large satellite constellations have been proposed that can drastically increase the existing orbital population in coming years. This approach will certainly not help in improving the space environment in the future; instead, it can worsen the space environment situation as recent studies shows. Also, space resources (i.e. orbital slots and frequencies) are limited to accommodate many more satellite projects from commercial and government organization in the future. So, there is a serious question of how the space industry can move forward to maintain a balance in controlling the future number of the satellite while accommodating many commercial or government space entities. This article also identifies two optimized approaches as a way forward for future satellite projects that can also enhance the effectiveness of space technology in the future.

Advances in high-speed means of transportation have provided a convenient and fast way of traveling. Besides, the high-speed transportation has impact on the number of accidents reported every year. The monitoring of accidents is significant for improving the rules and regulations for transportation to avoid future accidents. The accident monitoring is performed using different networks on the ground, in the air, in the water, and in the space. Furthermore, the Space Air Ground Integrated Network (SAGIN) provides enlargement of coverage for applications like accident monitoring. In this paper, a framework is proposed for monitoring of accidents using SAGIN along with communication protocol. In this work, a simulation for verification of the framework and visualization of the deployment is performed. The improvement of services offered by proposed framework is discussed for comprehending the benefits.

Recently, the security of public key security algorithms have been research extensively; besides, the utilization of public key cryptography requires key exchange protocol. The security of key exchange protocol is significant as it transmits the key and therefore, the security of public key algorithms depend on the security of key exchange protocol. In addition, the concept of Perfect Forward Secrecy (PFS) is evolving with the number of security threats. Traditionally, the key exchange protocols use asymmetric and symmetric to exchange session keys, which consumes more hardware resources and time for implementation. Moreover, these encryption based key exchange protocols requires several messages to exchange before sending the key, which cause delay in key exchange and consume bendwidth ineffciently. This work provides a new key exchange protocol with randomized initialization vector and advanced features for PFS. The proposed algorithm is simple and faster as compared to previous algorithms, the security of proposed algorithm is comparable to One Time Pad (OTP) algorithm.

The rapid development in the industrial sector has caused severe damage to the environment, which resulted in the occurrence of catastrophic disasters of high magnitude on earth. Moreover, the efforts for providing better early warnings and rescue operations during and after the disasters largely depend on communication protocol utilized for disaster management. Therefore, researchers are working to devise an efficient communication protocol for detection and communication of disasters. The communication protocol must comprise a methodology to transmit images of the disaster site effectively and facilitates communication between disaster site and disaster management centers. Presently, the disaster management is performed using terrestrial networks (using the Internet and mobile networks), space-ground networks (using satellites in different orbits), and air-ground networks (using Un-manned Aerial Vehicle and airships). Besides, the utilization of all devices in space, air, and ground can help to enhance the services for disaster management. In this work, Space-Air-Ground Integrated Network (SAGIN) is proposed to be used for disaster management. Moreover, a framework is proposed for the realization of the enhanced services using Internet Protocol (IP) for the detection and communication of disasters. Also, a comparison with the presently deployed networks is provided for comparison of services provided for disaster management.

The increase in the flow of information and high-speed communication has compelled researchers to use satellite networks for different applications. The satellite networks comprise different satellites in different orbits that require the data security algorithms for the providing security and privacy of consumers' information. The data security primarily consists of data confidentiality service, which is provided by data encryption algorithms. The data encryption algorithm for example AES algorithm is utilized in many applications, including the satellites. The challenges for AES algorithm utilization in satellite applications are high-speed computation, lightweight implementation, and catering the radiations in the space environment. In this work, optimizations are proposed for coping with the challenges in a data encryption algorithm for the space environment. Also, the high-throughput optimization for the AES algorithm is realized on FPGA, and it equated with previous work. Moreover, the recent security attacks, for instance the nonce misuse attack is challenging for the security of encryption algorithms. The high-throughput optimized encryption algorithm protects against the recent attacks by the modifications in the AES algorithm. Moreover, the security analysis is provided against the latest attacks for the validation of high-throughput optimizations.

Power semiconductor switches such as MOSFET are widely used in electric vehicles, electric trains, and power conversion systems. The prognostics and health monitoring (PHM) and reliability of the MOSFETS are critical in power electronic systems. The ON-state resistance of the MOSFETS is the primary and significant precursor of failure. In this paper, we present a data-driven approach to predict the change in ON-state resistance using Long-Short Term Memory (LSTM) Recurrent Neural Network (RNN). The experimental data are obtained by power cycling the MOSFET in thermal stress. The LSTM network's hyperparameters are optimized using Bayesian Optimization, which improves results and reduces time to develop the model. Our proposed Bayesian Optimized LSTM RNN (BO-LSTM RNN) gives good prediction accuracy using less number of layers. The model's performance is also analyzed using a small percentage of data used to train the LSTM RNN. The proposed model is also tested on different MOSFETS degradation data to prove the universality of the model using the same hyperparameters.

The satellite networks are used for technological enhancement in many fields including mobile communication (i.e. 5G technology). Similarly, the aviation industry is in process of adopting the satellite network for effective and efficient air traffic control for enhancing the safety of passengers and aircrafts. Recently, the space-based Automatic Dependent Surveillance-Broadcast (ADS-B) system is introduced for aviation industry as an advancement of existing radar-based surveillance. Moreover, this system has its limitations such as inefficient satellite network utilization, global adaptability, and many more; which advocates its ineffectiveness as an efficient surveillance system. The challenges faced by the aviation industry can be resolved by using heterogeneous networks such as the Space-Air-Ground Integrated Network (SAGIN). Therefore, in this work, challenges faced by aviation industry and lagging in current and under-development systems are discussed, besides, a framework based on SAGIN is proposed for air traffic control. Moreover, the Satellite Communication Protocol Specifications (SCPS) is proposed for air traffic control communication and the proposed framework is simulated.

The need to explore outer and deep space and make it more beneficial for mankind is emphasized in the space industry. But such exploration missions demand intensive attitude control even under a harsh and challenging environment. Due to these external interruptions, the actuators installed at the spacecraft may suffer degradation in its performance with time and may cause partial or complete mission failure. This paper presents a fixed-time robust, yet simple, passive fault-tolerant control for a class of rigid spacecraft with partial loss of actuator effectiveness, external disturbance, and inertial uncertainties. A quaternion presents the spacecraft's attitude dynamics. The error trajectories of angular velocity and attitude are made to converge rapidly to a smaller region around the equilibrium in a fixed time. The trajectories then asymptotically converge to equilibrium. Simulation results endorse the effectiveness of the presented robust fixed-time passive fault-tolerant controller.

This paper compares the performance of a robust model predictive control (MPC) with a nominal MPC. The robust scheme is applied to a nonlinear system with input constraints, bounded unknown additive disturbances, and uncertainties on the system states. The design of the robust controller relies on the linearized version of the nonlinear model along its trajectory. It comprises two components, one of which is obtained by a continuous-time MPC approach with tightened constraints for stabilizing the nominal system. The other one is chosen as standard LQR gain, ensuring that the error system trajectories lie in a particular invariant set. The controller is implemented in a digital environment and utilizes a continuous-time model and equations, vastly reducing the computational burden. Furthermore, with some plausible assumptions, the closed-loop system is demonstrated to have regional exponential stability around the origin. Simulation results verify the improvement in disturbance rejection property of the employed controller over nominal MPC.

Satellite communication is among those applications where data confidentiality is required, but at the same time, computational resources are limited as well as the delay is critical. For these types of applications, symmetric key encryption algorithms are preferred over asymmetric key algorithms, due to lower computational cost and faster speed of operation. Furthermore, due to various critical aspects of information security, using Perfect Forward Secrecy (PFS) in many communication applications is advantageous. There are two ways to achieve PFS; either a mechanism for new key generation is required, or some protocols are used for sharing new session keys before communication. Both of these ways, at minimum, append additional computational load and delay in communication, which are critical in satellite communication. This is probably the most significant barrier that satellites do not use PFS for every communication. This paper presents a novel encryption algorithm where a message key is generated such that later only Exclusive OR (XOR) operation can be used to produce the ciphertext. Hence, the proposed algorithm eliminates the need for two separate algorithms for message key generation and encryption for PFS. Security analysis and experimental results show that proposed encryption algorithm is not only secure but also faster and cheaper than the widely used AES-CTR encryption algorithm. Therefore it is suitable to be used in satellite communication for PFS.

Authenticity and integrity of data are two primary and critical information security services, which are generally provided together through data authentication algorithms in many of the modern-day communication applications. Cipher based Message Authentication Code (CMAC) is one of the widely used authentication algorithms and also recommended for space applications. Besides, CMAC has some limitations, such as security vulnerabilities and serial architecture. On the other hand, due to the advent and growth of Space Information Network (SIN) and the trend of miniaturization of satellites, lightweight, fast, high data rate supported algorithms are desired nowadays for satellite applications. This paper presents a new lightweight authentication algorithm which removes the shortcomings of the CMAC algorithm to provide more efficient and secure data authentication. Experimental results validate the performance superiority of the proposed algorithm over the CMAC algorithm.

The need for high-speed communication has led the research towards designing parallel architectural algorithms for data security. The utilization of the Advanced Encryption Standard in Counter mode (AES-CTR) in cipher-based Authenticated Encryption (AE) algorithms has realized the importance of a unique Initialization Vector (IV) for data security. The Synthetic Initialization Vector (SIV) is an improvement of a generic IV used in the AES-CTR algorithm for nonce misuse and key wrapping attacks. In this work, we have proposed a new AE algorithm with parallel architecture named as Parallel Cipher-based Message Authentication Code with SIV Algorithm (PCMAC-SIV). The PCMAC-SIV AE algorithm is consists of an AES-CTR algorithm and parallel implementation of the Cipher-based Message Authentication Code (CMAC) algorithm with SIV algorithm for avoiding nonce misuse. The proposed algorithm is implemented on FPGA for showing its utility for high throughput applications. In this work, we compared the proposed algorithm implementation with the AES-GCM -SIV algorithm. The experimental results show that the throughput of the proposed algorithm show higher throughput of 1.629 Gbps for single plaintext and 13.06 Gbps for eight plaintexts.

The major concern and basic requirement for control engineers, besides stability and trajectory tracking, is to consider and utilize available resources efficiently. It involves restriction of the energy consumption and associated costs in the presence of system constraints. Recently, such optimal control schemes and techniques that are constructed on the mathematical model of the system have been productively realized, both for linear and nonlinear systems, and are termed as Model Predictive Control (MPC). This paper deals with an Adaptive MPC for a nonlinear nonminimum phase single-link flexible joint manipulator (SFJM) system with constraints on the input control effort, states, and output. The non-linear system model is linearized along its trajectory. At each sampling interval, the quadratic optimization problem is solved. The optimum input control effort is implemented in Receding Horizon fashion. This meaningfully diminishes the computational burden involved in solving complex nonlinear differential equations and the associated non-convex optimization problem. The adaptive MPC offers performance which is comparable to Nonlinear Model Predictive Control (NMPC). In this paper, the closed-loop stability of the overall control scheme is presented, and its performance is matched to the general Linear MPC and NMPC. The simulation results show the superiority of the performance of adaptive MPC over linear MPC with a significant decrease in computational burden as compared to NMPC.

Advance Encryption Standard (AES) is an algorithm widely used for encryption, authentication, authenticated encryption as well as in security protocols for providing security services in many modern-day applications. The primary reasons for the extensive use of AES are its stronger security and faster speed than its competitors. In the AES algorithm, different keys derived from the main key are used in encryption rounds, to provide strength to the security of the algorithm. However, in standard AES key expansion algorithm, the sub-keys are derived sequentially, that is one after other. This dependence on the previous sub-key has two problems. Firstly, the key generation cannot be parallelized, secondly, if any single sub-key is known to the attacker, all the other sub-keys, including master key, can be extracted. Also, Differential Power Analysis attack is known effective on standard AES key schedule. In this paper, we proposed a new key parallelized expansion algorithm for AES. The proposed algorithm removes the dependence on other sub-keys to provide faster speed and enhanced security. The proposed algorithm has been implemented in MATLAB software and on FPGA. The results of implementation validate that the computational efficiency of the proposed algorithm is superior to standard AES Key expansion.

The increase in occurrences of disasters by nature and humans has caused great harm to the people living on this planet. This disaster (such as tsunami, floods, and earthquakes, etc.) causes destruction of property and even loss of human life. The abrupt response and rescue operation in case of a disaster can tremendously reduce the human casualties. The traditional disaster management system has been using terrestrial networks, space-ground and air-ground information networks. Although the disaster reports were generated using space-ground or air-ground information networks and the relief operations use these information networks. However, the combination of both space-ground and air-ground information networks can be utilized for real-time rescue operations. In this work, the proposed IP based Space Air Ground Information Network (SAGIN) provides a protocol for real-time rescue operation in case of a disaster. The utilization of proposed method realized that it not only resolves all these limitations posed by individual use of space- ground and air-ground information networks but also the rescue operation in case of a disaster can be revolutionized.

The growing number of threats and attacks on communication systems has encouraged researchers to identify methods for providing security for data communication. Besides the encryption and authentication algorithms provide data security services for communication systems. However, the recent attacks on communication systems reveal that the attacks utilize the analysis of plaintext/ciphertext to breach the security of communication systems. Therefore, the plaintext should be randomized to prevent correlation between ciphertext. In this work, an algorithm is proposed for increasing ciphertext randomness in Parallel Cipher-based Message Authentication Code (PCMAC) Algorithm. The proposed algorithm utilizes the high throughput of PCMAC authenticated encryption algorithm for providing high throughput and more randomized ciphertext. The proposed algorithm is implemented for generation of Initialization Vector (IV) using the GEFFE generator and right shift operation for creating randomness in the ciphertext. The comparisons result show that the proposed implementation is more randomized as compared to the previous implementation.

In the present, the use of communication systems is not a luxury but a necessity. The growing reliance on technology and its uses in all walk of life have realized the need for robust security systems for communication. The Advanced Encryption Standard (AES) in Counter (CTR) mode support high-speed operations due to parallel architecture and having no feedback or chaining mode. The AES-CTR algorithm involves encryption of Initialization Vector (IV) with a secret key for generation of ciphertext. A unique IV is required in the AES-CTR algorithm for maintaining the secrecy of data and generation of unique ciphertext. Previously, the researchers utilized the GEFFE generator for generation of IV as well as right-shift and increment operation were used for IV generation. The combination of these two algorithms can provide an increase in ciphertext randomness as compared to using it individually. In this work, we have proposed an IV generation algorithm based on the GEFFE generator and right-shift and increment operation for the AES-CTR algorithm. The proposed algorithm generates an increase in randomness for data security. The comparative analysis with other techniques shows that our algorithm has better in performance and security.

The advancements in communication technology have evolved the algorithms used for communication security. Recently, the Authenticated Encryption (AE) algorithms are employed for providing security services for data communication. The Advanced Encryption Standard in Counter mode (AES-CTR) with Cipher-block Chaining Message authentication code (AES-CCM) algorithm is used for providing the data security for various applications. But the AES-CCM algorithm provides limited throughput for data communication. Therefore, in this work, new architecture is proposed for increase in throughput for provision of data security for communication application. The proposed algorithm uses the AES-CTR algorithm with the Cipher-based Message Authentication Code (CMAC) algorithm for providing AE. The proposed AE algorithm is implemented on FPGA and it’s compared with the FPGA implementation of AES-CCM algorithm. The comparison results of the proposed algorithm and the AES-CCM algorithm shows that the proposed algorithm provides improvement in the consumption of the area, processing time, and throughput. The implementation of proposed AES-CMAC AE algorithm on FPGA provides a throughput of 4.30 Gbps.

Communication Navigation and Surveillance (CNS) are the three main components of air traffic management (ATC). The long due transformation of air traffic surveillance from old technology to modern technology is about to accomplish by the deployment of satellite-based ADS- B (Automatic Dependent Surveillance-Broadcast) technology. This will extend current airspace coverage from limited continental regions (30%) to a global (100%) coverage. However, communication, being the other critical component of air traffic control is still far behind such a major modernization as well as not ready to accompany this global nature of future air traffic. In our recent work, we have elaborated the limitations of space based-ADS-B system and proposed an alternate better solution in the form of IP-based Space Air Ground Information Network (SAGIN). This paper highlights the limitations and challenges of existing technologies of air traffic communication and issues of independent CNS. The work explained that the SAGIN could not only provide the required modernization of air traffic communication but at the same time, it can provide a reliable, unified and global platform for an integrated CNS for an efficient and global ATC.

The evolution in digital communication technology has provoked the need for providing efficient security services for communication. The data security services majorly includes; confidentiality, authenticity, and integrity services. The Authenticated Encryption (AE) algorithm provides all these three services. Initially, AE algorithms were proposed with serial architecture. These AE algorithms are low throughput as compared to parallel architecture algorithms such as Galois Counter Mode (GCM) algorithm. In this work, we have presented a new AE algorithm with parallel architecture named as Parallel Cipher-based Message Authentication Code (PCMAC). The PCMAC AE algorithm is consists of Advanced Encryption Standard (AES) algorithm in Counter mode (CTR) and parallel implementation of the CMAC authentication algorithm. The proposed PCMAC algorithm is implemented on FPGA for showing its utility for high throughput applications. In this work, we compared the PCMAC AE algorithm implementation with the GCM AE algorithm implementation. The experimental results show that the throughput of PCMAC algorithm for pipelined implementation is 41.45 Gbps.

During the last decade, the development of space technology for the benefits of humanity has been a significant area of research. The communication systems used in space technology is more sensitive to environmental effects than that used on earth. As in space, communication systems should withstand radiations, pressure, and vacuum effects. Therefore, the different types of radiations exposed to electronic hardware in space can cause anomalies in communication systems. Such anomalies can cause loss of data and even damage to equipment due to effects known as Single Event Effects (SEE). The security services in space are provided using encryption algorithms such as Advanced Encryption Standard (AES). In the AES algorithm, the Substitution Box (S-Box) implementation generally utilizes memory blocks. These memory blocks are mostly affected by SEE in the presence of radiations. There are two main techniques for implementing the S-box for the AES algorithm either by generating a predefined table or using an algorithm-based architecture for substitution. In this paper, we have analyzed the pros and cons of using these architectures for the implementation of the S-Box on FPGA. Moreover, experimental results show that the algorithm-based architectural implementation is more SEE tolerant and more suitable for satellite application.

The commercial aviation industry mainly relies on ground-based radar system for air traffic surveillance. This traditional system has a fundamental shortcoming of limited coverage. The outcome of this limitation is expensive nonlinear airplane routing, inefficient utilization of air space, incidents like missing airplane and damaged black box that results in mystery about the cause of the accident, etc. In the recent decade, Automatic Dependent Surveillance-Broadcast (ADS-B) technology is considered for deployment by international aviation authorities as an advance alternate. The space-based ADS-B is recently considered more promising & useful than ground-based ADS-B. Owing to many advantages over the existing radar-based system, it is anticipated by the aviation industry to switch from radar-based system to ADS-B eventually. However, we have highlighted that even space-based ADS-B have some limitations that will prevent it from becoming a single surveillance system for ATC, and restricts it to be only additional support for the existing surveillance system. With the help of our recently proposed Space Air Ground Information Network (SAGIN), we have enlightened that utilization of space information network can resolve not only all these limitations but also aviation industry can be revolutionized.

In communication systems, data encryption and authentication algorithms are utilized for secure communication. The utilization of encryption and authentication algorithms depends on the field of application and required level of security. Recently, researchers are working on encryption based authentication algorithms, as both services of encryption and authentication are utilized in highly secure systems such as satellite communication. The Cipher based Message Authentication Code (CMAC) finds its relevance in many applications. CMAC algorithm has been implemented previously on software and hardware. But by assessment of previous work on hardware implementation it seems that competence could be enhanced by efficiently utilizing hardware resources. In this paper, an improved and efficient hardware implementation of CMAC algorithm on FPGA is proposed for satellites application. Our results showed improvement in consumption of FPGA area and time utilization as compared to previous implementations.

In this era of information technology, information security is a major concern. To address the challenges of data security, cryptography is used for storage as well as for the communication of data. A cryptographic algorithm has two main performance characteristics: the ability to secure data against different attacks and the processing speed. An algorithm is considered secure if no attack exists to reveal the original contents without knowing the key. The strength of any secure encryption algorithm is, therefore, generally measured based on the difficulty to obtain the encryption key through cyber-attacks such as brute force. It is presumed that the bigger the key size, the more difficult it is for the attacker to compute the key. Consequently, increasing the key size generally increases the computational complexity and processing time of algorithms. As a result, an established assumption is the existence of a tradeoff and computational complexity. In this paper, we are presenting an alternate symmetric key encryption algorithm, which can easily avoid long and complex computation of conventional popular symmetric key encryption algorithms such as the Data Encryption Standards and the Advance Encryption Standard. We have shown that despite providing a higher level of security, one simplest software implementation of our algorithm is faster than some previously implemented conventional algorithms. Additionally, our algorithm also provides other advantages such as inherent data compression option and flexibility of choosing different complexity levels according to the need for different applications.

In this paper, a new scheme to enhance security of wireless gateway node is presented. In proposed scheme, analysis of implementing counter with cipher block chaining message authentication code on field programmable gate array has been proposed. Preliminary results show that proposed scheme does not have application dependency and have potential to be integrated with any application of wireless sensor network.

In field of image processing and pattern recognition, the use of edges as a feature is significant for feature extraction owing to its simplicity and accuracy. Its areas of application vary from object recognition to satellite based terrain recognition. There are many edge detection techniques like the canny edge detector and Sobel edge detector etc. However, the quality of an efficient algorithm depends on its capability to generate well localized edges of real images. Noise is inherent in all real images. To reduce its effect, various smoothing low pass filters are used prior to edge detection. This work, compares edge detection based on bilateral filtering with canny edge detection technique for satellite Images. Bilateral filtering based edge detection not only generates well localized edges but also simultaneously reduces considerable noise from real life images. The results show that the bilateral filtering based edge detection provide better edge maps than other comparable techniques.

Vehicle detection is becoming a necessary part of Automatic Cruise Control (ACC) and Advanced Driver Assistance Systems (ADAS). Our main focus in this paper is on improving the performance of single camera based vehicle detection systems. Edges are one of the main characteristics of an object, which carries most of the information about an object in an image. In this paper, it was observed that horizontal edges are strong feature for vehicle detection. Therefore, we generated initial candidate using Horizontal Edge Filtering (HEF) on canny edge map. These initial candidates are further verified using Bag-of-Features (BoF) with K nearest neighbor algorithm. A threshold is used on differences of histograms of training and test images for matching the vehicles. In this paper, the combination of edges (initial candidate) and bag-of-features (final verification) has improved detection rate significantly as compared to other well known methods. Our method has 96% detection rate on roads inside a city and 98% detection on highways.

Edge detection has been the foremost step in image processing and computer vision, because an edge representation drastically reduces the amount of data to be processed. Although classical methods of edge detection like Sobel, Canny, etc. are simple to use but has a dilemma between noise removal and edge localization. If noise is to be removed by using a low pass filter then edges are blurred. However, if edges have to be preserved then noise severly corrupts the edge map. In this paper, we have proposed a new method of edge detection, BiGaussian edge Filter, which simultaneously removes noise from real life images, while generating well localized edges. We have compared our method using images form Berkely’s segmentation data set. Experimental results show the robustness of our method to noise in real life images.

Hand gestures can be used for natural and intuitive human-computer interaction. Our new method combines existing techniques of skin color based ROI segmentation and Viola-Jones Haar-like feature based object detection, to optimize hand gesture recognition for mouse operation. A mouse operation has two parts, movement of cursor and clicking using the right or left mouse button. In this paper, color is used as a robust feature to first define a Region of Interest (ROI). Then within this ROI, hand postures are detected by using Haar-like features and AdaBoost learning algorithm. The AdaBoost learning algorithm significantly speeds up the performance and constructs an accurate cascaded classifier by combining a sequence of weak classifiers.