Search

Recent advancements in predicting pedestrian crossing intentions for Autonomous Vehicles using Computer Vision and Deep Neural Networks are promising. However, the black-box nature of DNNs poses challenges in understanding how the model works and how input features contribute to final predictions. This lack of interpretability delimits the trust in model performance and hinders informed decisions on feature selection, representation, and model optimisation; thereby affecting the efficacy of future research in the field. To address this, we introduce Context-aware Permutation Feature Importance (CAPFI), a novel approach tailored for pedestrian intention prediction. CAPFI enables more interpretability and reliable assessments of feature importance by leveraging subdivided scenario contexts, mitigating the randomness of feature values through targeted shuffling. This aims to reduce variance and prevent biased estimations in importance scores during permutations. We divide the Pedestrian Intention Estimation (PIE) dataset into 16 comparable context sets, measure the baseline performance of five distinct neural network architectures for intention prediction in each context, and assess input feature importance using CAPFI. We observed nuanced differences among models across various contextual characteristics. The research reveals the critical role of pedestrian bounding boxes and ego-vehicle speed in predicting pedestrian intentions, and potential prediction biases due to the speed feature through cross-context permutation evaluation. We propose an alternative feature representation by considering proximity change rate for rendering dynamic pedestrian-vehicle locomotion, thereby enhancing the contributions of input features to intention prediction. These findings underscore the importance of contextual features and their diversity to develop accurate and robust intent-predictive models.

Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essential computer vision tasks, such as semantic segmentation, and often focus on only one specific condition, such as removing rain or translating nighttime images into daytime ones. To address these limitations, we propose a method to improve the visual quality and clarity degraded by such adverse conditions. Our method, AllWeather-Net, utilizes a novel hierarchical architecture to enhance images across all adverse conditions. This architecture incorporates information at three semantic levels: scene, object, and texture, by discriminating patches at each level. Furthermore, we introduce a Scaled Illumination-aware Attention Mechanism (SIAM) that guides the learning towards road elements critical for autonomous driving perception. SIAM exhibits robustness, remaining unaffected by changes in weather conditions or environmental scenes. AllWeather-Net effectively transforms images into normal weather and daytime scenes, demonstrating superior image enhancement results and subsequently enhancing the performance of semantic segmentation, with up to a 5.3% improvement in mIoU in the trained domain. We also show our model's generalization ability by applying it to unseen domains without re-training, achieving up to 3.9% mIoU improvement. Code can be accessed at: https://github.com/Jumponthemoon/AllWeatherNet.

Accurate pedestrian intention prediction (PIP) by Autonomous Vehicles (AVs) is one of the current research challenges in this field. In this article, we introduce PIP-Net, a novel framework designed to predict pedestrian crossing intentions by AVs in real-world urban scenarios. We offer two variants of PIP-Net designed for different camera mounts and setups. Leveraging both kinematic data and spatial features from the driving scene, the proposed model employs a recurrent and temporal attention-based solution, outperforming state-of-the-art performance. To enhance the visual representation of road users and their proximity to the ego vehicle, we introduce a categorical depth feature map, combined with a local motion flow feature, providing rich insights into the scene dynamics. Additionally, we explore the impact of expanding the camera's field of view, from one to three cameras surrounding the ego vehicle, leading to enhancement in the model's contextual perception. Depending on the traffic scenario and road environment, the model excels in predicting pedestrian crossing intentions up to 4 seconds in advance which is a breakthrough in current research studies in pedestrian intention prediction. Finally, for the first time, we present the Urban-PIP dataset, a customised pedestrian intention prediction dataset, with multi-camera annotations in real-world automated driving scenarios.

As automated driving technology advances, the role of the driver to resume control of the vehicle in conditionally automated vehicles becomes increasingly critical. In the SAE Level 3 or partly automated vehicles, the driver needs to be available and ready to intervene when necessary. This makes it essential to evaluate their readiness accurately. This article presents a comprehensive analysis of driver readiness assessment by combining head pose features and eye-tracking data. The study explores the effectiveness of predictive models in evaluating driver readiness, addressing the challenges of dataset limitations and limited ground truth labels. Machine learning techniques, including LSTM architectures, are utilised to model driver readiness based on the Spatio-temporal status of the driver's head pose and eye gaze. The experiments in this article revealed that a Bidirectional LSTM architecture, combining both feature sets, achieves a mean absolute error of 0.363 on the DMD dataset, demonstrating superior performance in assessing driver readiness. The modular architecture of the proposed model also allows the integration of additional driver-specific features, such as steering wheel activity, enhancing its adaptability and real-world applicability.

Autonomous vehicles (AVs) are becoming an indispensable part of future transportation. However, safety challenges and lack of reliability limit their real-world deployment. Towards boosting the appearance of AVs on the roads, the interaction of AVs with pedestrians including "prediction of the pedestrian crossing intention" deserves extensive research. This is a highly challenging task as involves multiple non-linear parameters. In this direction, we extract and analyse spatio-temporal visual features of both pedestrian and traffic contexts. The pedestrian features include body pose and local context features that represent the pedestrian's behaviour. Additionally, to understand the global context, we utilise location, motion, and environmental information using scene parsing technology that represents the pedestrian's surroundings, and may affect the pedestrian's intention. Finally, these multi-modality features are intelligently fused for effective intention prediction learning. The experimental results of the proposed model on the JAAD dataset show a superior result on the combined AUC and F1-score compared to the state-of-the-art.

Accurate lane change prediction can reduce potential accidents and contribute to higher road safety. Adaptive cruise control (ACC), lane departure avoidance (LDA), and lane keeping assistance (LKA) are some conventional modules in advanced driver assistance systems (ADAS). Thanks to vehicle-to-vehicle communication (V2V), vehicles can share traffic information with surrounding vehicles, enabling cooperative adaptive cruise control (CACC). While ACC relies on the vehicle's sensors to obtain the position and velocity of the leading vehicle, CACC also has access to the acceleration of multiple vehicles through V2V communication. This paper compares the type of information (position, velocity, acceleration) and the number of surrounding vehicles for driver lane change prediction. We trained an LSTM (Long Short-Term Memory) on the HighD dataset to predict lane change intention. Results indicate a significant improvement in accuracy with an increase in the number of surrounding vehicles and the information received from them. Specifically, the proposed model can predict the ego vehicle lane change with 59.15% and 92.43% accuracy in ACC and CACC scenarios, respectively.

The development of Adaptive Cruise Control (ACC) systems aims to enhance the safety and comfort of vehicles by automatically regulating the speed of the vehicle to ensure a safe gap from the preceding vehicle. However, conventional ACC systems are unable to adapt themselves to changing driving conditions and drivers' behavior. To address this limitation, we propose a Long Short-Term Memory (LSTM) based ACC system that can learn from past driving experiences and adapt and predict new situations in real time. The model is constructed based on the real-world highD dataset, acquired from German highways with the assistance of camera-equipped drones. We evaluated the ACC system under aggressive lane changes when the side lane preceding vehicle cut off, forcing the targeted driver to reduce speed. To this end, the proposed system was assessed on a simulated driving environment and compared with a feedforward Artificial Neural Network (ANN) model and Model Predictive Control (MPC) model. The results show that the LSTM-based system is 19.25% more accurate than the ANN model and 5.9% more accurate than the MPC model in terms of predicting future values of subject vehicle acceleration. The simulation is done in Matlab/Simulink environment.

Aiming at highly accurate object detection for connected and automated vehicles (CAVs), this paper presents a Deep Neural Network based 3D object detection model that leverages a three-stage feature extractor by developing a novel LIDAR-Camera fusion scheme. The proposed feature extractor extracts high-level features from two input sensory modalities and recovers the important features discarded during the convolutional process. The novel fusion scheme effectively fuses features across sensory modalities and convolutional layers to find the best representative global features. The fused features are shared by a two-stage network: the region proposal network (RPN) and the detection head (DH). The RPN generates high-recall proposals, and the DH produces final detection results. The experimental results show the proposed model outperforms more recent research on the KITTI 2D and 3D detection benchmark, particularly for distant and highly occluded instances.

In this paper, we investigate the application of end-to-end and multi-module frameworks for G2P conversion for the Persian language. The results demonstrate that our proposed multi-module G2P system outperforms our end-to-end systems in terms of accuracy and speed. The system consists of a pronunciation dictionary as our look-up table, along with separate models to handle homographs, OOVs and ezafe in Persian created using GRU and Transformer architectures. The system is sequence-level rather than word-level, which allows it to effectively capture the unwritten relations between words (cross-word information) necessary for homograph disambiguation and ezafe recognition without the need for any pre-processing. After evaluation, our system achieved a 94.48% word-level accuracy, outperforming the previous G2P systems for Persian., Comment: 10 pages, 4 figures

Computer Vision has played a major role in Intelligent Transportation Systems (ITS) and traffic surveillance. Along with the rapidly growing automated vehicles and crowded cities, the automated and advanced traffic management systems (ATMS) using video surveillance infrastructures have been evolved by the implementation of Deep Neural Networks. In this research, we provide a practical platform for real-time traffic monitoring, including 3D vehicle/pedestrian detection, speed detection, trajectory estimation, congestion detection, as well as monitoring the interaction of vehicles and pedestrians, all using a single CCTV traffic camera. We adapt a custom YOLOv5 deep neural network model for vehicle/pedestrian detection and an enhanced SORT tracking algorithm. For the first time, a hybrid satellite-ground based inverse perspective mapping (SG-IPM) method for camera auto-calibration is also developed which leads to an accurate 3D object detection and visualisation. We also develop a hierarchical traffic modelling solution based on short- and long-term temporal video data stream to understand the traffic flow, bottlenecks, and risky spots for vulnerable road users. Several experiments on real-world scenarios and comparisons with state-of-the-art are conducted using various traffic monitoring datasets, including MIO-TCD, UA-DETRAC and GRAM-RTM collected from highways, intersections, and urban areas under different lighting and weather conditions.

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and optimised behaviour. In this paper, we focus on training a single agent to score goals with binary success/failure reward function in Half Field Offense domain. As the major advantage of this research, the agent has no presumption about the environment which means it only follows the original formulation of reinforcement learning agents. The main challenge of using such a reward function is the high sparsity of positive reward signals. To address this problem, we use a simple prediction-based exploration strategy (called Curious Exploration) along with a Return-based Memory Restoration (RMR) technique which tends to remember more valuable memories. The proposed method can be utilized to train agents in environments with fairly complex state and action spaces. Our experimental results show that many recent solutions including our baseline method fail to learn and perform in complex soccer domain. However, the proposed method can converge easily to the nearly optimal behaviour. The video presenting the performance of our trained agent is available at http://bit.ly/HFO_Binary_Reward.

In this paper, we present an active vision method using a deep reinforcement learning approach for a humanoid soccer-playing robot. The proposed method adaptively optimises the viewpoint of the robot to acquire the most useful landmarks for self-localisation while keeping the ball into its viewpoint. Active vision is critical for humanoid decision-maker robots with a limited field of view. To deal with an active vision problem, several probabilistic entropy-based approaches have previously been proposed which are highly dependent on the accuracy of the self-localisation model. However, in this research, we formulate the problem as an episodic reinforcement learning problem and employ a Deep Q-learning method to solve it. The proposed network only requires the raw images of the camera to move the robot's head toward the best viewpoint. The model shows a very competitive rate of 80% success rate in achieving the best viewpoint. We implemented the proposed method on a humanoid robot simulated in Webots simulator. Our evaluations and experimental results show that the proposed method outperforms the entropy-based methods in the RoboCup context, in cases with high self-localisation errors., Comment: The paper has been accepted in ICAART 2021

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-meter physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a hybrid Computer Vision and YOLOv4-based Deep Neural Network model for automated people detection in the crowd in indoor and outdoor environments using common CCTV security cameras. The proposed DNN model in combination with an adapted inverse perspective mapping (IPM) technique and SORT tracking algorithm leads to a robust people detection and social distancing monitoring. The model has been trained against two most comprehensive datasets by the time of the research the Microsoft Common Objects in Context (MS COCO) and Google Open Image datasets. The system has been evaluated against the Oxford Town Centre dataset with superior performance compared to three state-of-the-art methods. The evaluation has been conducted in challenging conditions, including occlusion, partial visibility, and under lighting variations with the mean average precision of 99.8% and the real-time speed of 24.1 fps. We also provide an online infection risk assessment scheme by statistical analysis of the Spatio-temporal data from people's moving trajectories and the rate of social distancing violations. The developed model is a generic and accurate people detection and tracking solution that can be applied in many other fields such as autonomous vehicles, human action recognition, anomaly detection, sports, crowd analysis, or any other research areas where the human detection is in the centre of attention.

One of the most challenging and non-trivial tasks in robot-based rescue operations is the Hazardous Materials or HAZMATs sign detection in the operation field, to prevent further unexpected disasters. Each Hazmat sign has a specific meaning that the rescue robot should detect and interpret it to take a safe action, accordingly. Accurate Hazmat detection and real-time processing are the two most important factors in such robotics applications. Furthermore, we also have to cope with some secondary challenges such as image distortion and restricted CPU and computational resources which are embedded in a rescue robot. In this paper, we propose a CNN-Based pipeline called DeepHAZMAT for detecting and segmenting Hazmats in four steps; 1) optimising the number of input images that are fed into the CNN network, 2) using the YOLOv3-tiny structure to collect the required visual information from the hazardous areas, 3) Hazmat sign segmentation and separation from the background using GrabCut technique, and 4) post-processing the result with morphological operators and convex hull algorithm. In spite of the utilisation of a very limited memory and CPU resources, the experimental results show the proposed method has successfully maintained a better performance in terms of detection-speed and detection-accuracy, compared with the state-of-the-art methods.

Automated human action recognition is one of the most attractive and practical research fields in computer vision, in spite of its high computational costs. In such systems, the human action labelling is based on the appearance and patterns of the motions in the video sequences; however, the conventional methodologies and classic neural networks cannot use temporal information for action recognition prediction in the upcoming frames in a video sequence. On the other hand, the computational cost of the preprocessing stage is high. In this paper, we address challenges of the preprocessing phase, by an automated selection of representative frames among the input sequences. Furthermore, we extract the key features of the representative frame rather than the entire features. We propose a hybrid technique using background subtraction and HOG, followed by application of a deep neural network and skeletal modelling method. The combination of a CNN and the LSTM recursive network is considered for feature selection and maintaining the previous information, and finally, a Softmax-KNN classifier is used for labelling human activities. We name our model as Feature Reduction & Deep Learning based action recognition method, or FR-DL in short. To evaluate the proposed method, we use the UCF dataset for the benchmarking which is widely-used among researchers in action recognition research. The dataset includes 101 complicated activities in the wild. Experimental results show a significant improvement in terms of accuracy and speed in comparison with six state-of-the-art articles.

CAPTCHA is a human-centred test to distinguish a human operator from bots, attacking programs, or other computerised agents that tries to imitate human intelligence. In this research, we investigate a way to crack visual CAPTCHA tests by an automated deep learning based solution. The goal of this research is to investigate the weaknesses and vulnerabilities of the CAPTCHA generator systems; hence, developing more robust CAPTCHAs, without taking the risks of manual try and fail efforts. We develop a Convolutional Neural Network called Deep-CAPTCHA to achieve this goal. The proposed platform is able to investigate both numerical and alphanumerical CAPTCHAs. To train and develop an efficient model, we have generated a dataset of 500,000 CAPTCHAs to train our model. In this paper, we present our customised deep neural network model, we review the research gaps, the existing challenges, and the solutions to cope with the issues. Our network's cracking accuracy leads to a high rate of 98.94% and 98.31% for the numerical and the alpha-numerical test datasets, respectively. That means more works is required to develop robust CAPTCHAs, to be non-crackable against automated artificial agents. As the outcome of this research, we identify some efficient techniques to improve the security of the CAPTCHAs, based on the performance analysis conducted on the Deep-CAPTCHA model., Comment: Version 2.0

The challenge of learning a new concept, object, or a new medical disease recognition without receiving any examples beforehand is called Zero-Shot Learning (ZSL). One of the major issues in deep learning based methodologies such as in Medical Imaging and other real-world applications is the requirement of large annotated datasets prepared by clinicians or experts to train the model. ZSL is known for having minimal human intervention by relying only on previously known or trained concepts plus currently existing auxiliary information. This makes the ZSL applicable in many real-world scenarios, from unknown object detection in autonomous vehicles to medical imaging and unforeseen diseases such as COVID-19 Chest X-Ray (CXR) based diagnosis. We introduce a novel and broaden solution called Few/one-shot learning, and present the definition of the ZSL problem as an extreme case of the few-shot learning. We review over fundamentals and the challenging steps of Zero-Shot Learning, including state-of-the-art categories of solutions, as well as our recommended solution, motivations behind each approach, their advantages over each category to guide both clinicians and AI researchers to proceed with the best techniques and practices based on their applications. We then review through different datasets inducing medical and non-medical images, the variety of splits, and the evaluation protocols proposed so far. Finally, we discuss the recent applications and future directions of ZSL. We aim to convey a useful intuition through this paper towards the goal of handling complex learning tasks more similar to the way humans learn. We mainly focus on two applications in the current modern yet challenging era: coping with an early and fast diagnosis of COVID-19 cases, and also encouraging the readers to develop other similar AI-based automated detection/recognition systems using ZSL., Comment: Accepted in Journal of Intelligence-Based Medicine (Elsevier)