Search

Datasets are the important part of vehicle re-identification (re-id) research. The dataset which represents real world environment is crucial to vehicle re-id steps such as learning visual features, vehicle detection, examining performance of vehicle re-id algorithms, and so on. Often vehicle re-id datasets lacks in this context. In this paper, firstly, we investigate the vehicle re-id datasets bias problem using deep CNN model inception-v3 (Dataset classification). Dataset classification results indicates that current available vehicle re-id datasets are highly biased. Secondly, we present novel data augmentation technique to mitigate this issue by inserting additional type of variability in training set. Extensive experimental results shows that our approach can be helpful to minimize training set bias. Consequently, cross dataset vehicle re-id performance improves.

We present a voted optimization algorithm utilizing correlation of adjacent frames’ texture feature and thoughts of voted selection for newly proposed video standard High Efficiency Video Coding (HEVC). In addition, a voted algorithm based on original candidate mode collection is developed, which use the candidate modes, to resolve HEVC Most Probable Mode (MPM) mechanism for intra prediction problem. Meanwhile, we perform the vote rules to cut down on candidate collection, which is based on our proposed voted method. Experimental results show that proposed voted algorithm improves the efficiency of encoder by decreasing encoding time with more than 20% and causes nearly negligible increment in bit-rate.

In recent years, vehicle recognition has become an important application in intelligent traffic monitoring and management. In this paper, we proposed a deep convolution neural network which is no less than nine layers. A vehicle data set is employed which is collected from multiple perspectives and the deep learning framework Caffe is used to verify the proposed algorithm. Comparing with traditional vehicle recognition based on machine learning which needs vehicle location and has low accuracy of shortcomings, the proposed model uses deep convolution neural network has a better performance.

Due to growth of vehicles in urban cities, such problems are increases traffic control systems, security and crime investigation, intelligent parking and electronic toll collection. Moreover, Logistics access management system (LMS)is also a big problem in urban cities and all the issues are challenging and demands to develop effective and efficient approach for vehicle classification. Mostly, traditional vehicle classification uses hand craft feature extraction method like SIFT, Surf, HoG etc. However, these approaches are not efficient in results. This paper presents the efficient framework for vehicle classification by using Inception-v3 model for image vector features extraction that is most advance deep learning neural network, and this model is not used before for vehicle classification. After that, different classification algorithms are implemented on the feature vector. The classification conducted on three vehicle datasets and results demonstration is helpful for researchers to choose dataset with algorithm performance.

Vehicle re-identification (Re-Id) is the key module in an intelligent transportation system (ITS). Due to its versatile applicability in metropolitan cities, this task has received increasing attention these days. It aims to identify whether the specific vehicle has already appeared over the surveillance network or not. Mostly, the vehicle Re-Id method are evaluated on a single dataset, in which training and testing of the model is performed on the same dataset. However in practice, this negatively effects model generalization ability due to biased datasets along with the significant difference between training and testing data, hence, the model becomes weak in a practical environment. To demonstrate this issue, we have empirically shown that the current vehicle Re-Id datasets are usually strongly biased. In this regard, we also conduct an extensive study on the cross and the same dataset to examine the impact on the performance of the vehicle Re-Id system, considering existing methods. To address the problem, in this paper, we have proposed an approach with augmentation of the training dataset to reduce the influence of pose, angle, camera color response, and background information in vehicle images, whereas, spatio-temporal patterns of unlabelled target datasets are learned by transferring siamese neural network classifiers trained on a source-labelled dataset. We finally calculate the composite similarity score of spatio-temporal patterns with siamese neural-network-based classifier visual features. Extensive experiments on multiple datasets are examined and results suggest that the proposed approach has the ability to generalize adequately.

This paper identifies the concept of effective multimedia computer aided learning software to tackle students fear or inability to figure out solutions. This also discussed of how to solve mathematical problems which are basic building blocks for virtually all sciences. The presented arguments are detailed utilizing the waterfall model as its methodology for the design and implementation of a multimedia computer aided learning software where each process takes a product input, transforms this product input and produces another product as output. The overall paper has discussed the insight and the methodology is discussed with evidence to support the argument.

this paper is based on the use of group work to facilitate learning in tertiary institutions. A collaborative learning approach for integrated time based online environment is developed for both students and their project supervisors to eliminate or reduce lapses. The web application enables a project supervisor or lecturer to create and assign tasks to students in groups, specifying the time for collaborative activities at which the members of the group are expected to login to the website and work cooperatively and collaboratively under the supervision of the supervisor or lecturer. Rapid Application Development (RAD) methodology is used. The model is implemented with the PHP Framework which handles the server side and Bootstrap for HTML, CSS, JavaScript and jQuery which handles the frontend. MySQL is employed for the database management. After the implementation of the system, it was tested with some input queries and the result shows that the system is effective and realistic. Hence, the proposed system offers a solution to the defects of the traditional collaborative learning to lecturers as well as students.

Antenatal classes are sometimes called parentcraft which help to prepare expectant mothers for their baby's birth, feeding the baby and to look after the baby. It is the best way to ensure expectant mothers stay healthy during pregnancy as well as to deliver confidence and information. This paper looks into the current state of antenatal education. It investigates the way antenatal classes are accessed by expectant mothers, the challenges they face in getting access to these classes and their attitudes towards these classes. For most women, it could be stressful and very inconvenient to attend physical antenatal classes. An online collaborative approach of interactive antenatal lecture for expectant mothers is proposed to replace these classes by providing live streaming lectures, discussion and interactive sessions between users. In order to accomplish this task, some face-to-face interviews were conducted. Questionnaires were also distributed. This paper adopted the Structured Systems Analysis and Design Method (SSADM) for the specification, development, and implementation. The web based system is implemented using PHP framework as Back-end, Front-End using HTML, CSS, JavaScript, XAMPP Server and MySQL was employed to handle the database structure. The web based system was implemented and tested using carefully thought out test cases which were successful. The proposed system offers antenatal education to expectant mothers no matter their location as well as a platform for discussion between expectant mothers, midwives, or anyone at all; sharing useful information amongst themselves and giving advice and encouragement to one another.

This paper proposes a simple but efficient android-based information system for marriage counseling. The information system developed also contains a self-evaluation module in the form of quiz. The methodology adopted in the development of the system is the Rapid Application Development Methodology. The programming language used is Java and XML as the markup language. The contents of the database are gotten from online sources authored by experts on Marriage counseling. Hence, the solutions provided by the system will work well in real life scenarios except in exceptional cases.

Clearance for graduating students is necessarily a continual process in every University. Clearance has always been manual processes over the past years. This paper aims at improving the existing system by exploring its weaknesses. Front-End Languages used are HTML for building the web pages, CSS for styling the web pages, JavaScript for programming web pages, Sublime Text 3 for code editor, PHP for the Back-End, MySQL for the database and the XAMPP servers are used for the design and implementation of the proposed system. The methodology used in this paper is Structured System Analysis and Design (SSADM). The proposed system reduces process time, loss of documents, document forgery and physical presence by eliminating paper work which makes it more efficient, secure and reliable over the existing method. It also incorporates payment options for convenience. The results in this paper show that electronic clearance processing time was reduced significantly that gave rise to an efficient and reliable electronic clearance system for graduating students.

Today, artificial intelligence (AI) has become more and more popular in daily life, such as face recognition, speech recognition, automated driving. In this paper, corrected neural model is proposed, where the deep learning framework Caffe is used to verify the proposed model. In this case, a face dataset and a car dataset collected from multiple perspectives are employed. Results show that the proposed corrected network model has great contributes to improve the accuracy of object recognition.

Nowadays, artificial intelligence has become more and more popular in daily life. In this paper, a ten-layer network model which is based on residual thought is proposed. And the deep learning framework Caffe is used to verify the proposed algorithm where a face dataset and a car dataset collected from multiple perspectives are employed. Results show that the proposed residual network model contributes to improve the accuracy of recognition.

Nowadays, Radio Frequency Identification (RFID) technology has recently aroused great interest due to its convenience and economic efficiency, and the RFID technology has become mature and its manufacturing cost is reduced constantly, this technology has already widely used in a lot of field such as supply chain management, entrance guard system, intelligent home appliances, electronic payment, production automation, etc. But it also threatens security and privacy of individuals and organizations. So to effectively answering the challenges of security and privacy, in this work, we introduce a new way to authentication and encryption that use Sim card.