Although there are well established object detection methods based on static images, their application to video data on a frame by frame basis faces two shortcomings: (i) lack of computational efficiency due to redundancy across image frames or by not using a temporal and spatial correlation of features across image frames, and (ii) lack of robustness to real-world conditions such as motion blur and occlusion. Since the introduction of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2015, a growing number of methods have appeared in the literature on video object detection, many of which have utilized deep learning models. The aim of this paper is to provide a review of these papers on video object detection. An overview of the existing datasets for video object detection together with commonly used evaluation metrics is first presented. Video object detection methods are then categorized and a description of each of them is stated. Two comparison tables are provided to see their differences in terms of both accuracy and computational efficiency. Finally, some future trends in video object detection to address the challenges involved are noted.

This paper presents the simultaneous utilization of video images and inertial signals that are captured at the same time via a video camera and a wearable inertial sensor within a fusion framework in order to achieve a more robust human action recognition compared to the situations when each sensing modality is used individually. The data captured by these sensors are turned into 3D video images and 2D inertial images that are then fed as inputs into a 3D convolutional neural network and a 2D convolutional neural network, respectively, for recognizing actions. Two types of fusion are considered—Decision-level fusion and feature-level fusion. Experiments are conducted using the publicly available dataset UTD-MHAD in which simultaneous video images and inertial signals are captured for a total of 27 actions. The results obtained indicate that both the decision-level and feature-level fusion approaches generate higher recognition accuracies compared to the approaches when each sensing modality is used individually. The highest accuracy of 95.6% is obtained for the decision-level fusion approach.

Connected and Autonomous Vehicles (CAVs) combine technologies of autonomous vehicles (AVs) and connected vehicles (CVs) to develop quicker, more reliable, and safer traffic. Artificial Intelligence (AI)-based CAV solutions play significant roles in sustainable cities. The convergence imposes stringent security requirements for CAV safety and reliability. In practice, vehicles are developed with increased automation and connectivity. Increased automation increases the reliance on the sensor-based technologies and decreases the reliance on the driver; increased connectivity increases the exposures of vehicles’ vulnerability and increases the risk for an adversary to implement a cyber-attack. Much work has been dedicated to identifying the security vulnerabilities and recommending mitigation techniques associated with different sensors, controllers, and connection mechanisms, respectively. However, there is an absence of comprehensive and in-depth studies to identify how the cyber-attacks exploit the vehicles’ vulnerabilities to negatively impact the performance and operations of CAVs. In this survey, we set out to thoroughly review the security issues introduced by AV and CV technologies, analyze how the cyber-attacks impact the performance of CAVs, and summarize the solutions correspondingly. The impact of cyber-attacks on the performance of CAVs is elaborated from both viewpoints of intra-vehicle systems and inter-vehicle systems. We pointed out that securing the perception and operations of CAVs would be the top requirement to enable CAVs to be applied safely and reliably in practice. Additionally, we suggested to utilize cloud and new AI methods to defend against smart cyber-attacks on CAVs.

This paper addresses real-time moving object detection with high accuracy in high-resolution video frames. A previously developed framework for moving object detection is modified to enable real-time processing of high-resolution images. First, a computationally efficient method is employed, which detects moving regions on a resized image while maintaining moving regions on the original image with mapping coordinates. Second, a light backbone deep neural network in place of a more complex one is utilized. Third, the focal loss function is employed to alleviate the imbalance between positive and negative samples. The results of the extensive experimentations conducted indicate that the modified framework developed in this paper achieves a processing rate of 21 frames per second with 86.15% accuracy on the dataset SimitMovingDataset, which contains high-resolution images of the size 1920 × 1080.

Existing public domain multi-modal datasets for human action recognition only include actions of interest that have already been segmented from action streams. These datasets cannot be used to study a more realistic action recognition scenario where actions of interest occur randomly and continuously among actions of non-interest or no actions. It is more challenging to recognize actions of interest in continuous action streams since the starts and ends of these actions are not known and need to be determined in an on-the-fly manner. Furthermore, there exists no public domain multi-modal dataset in which video and inertial data are captured simultaneously for continuous action streams. The main objective of this paper is to describe a dataset that is collected and made publicly available, named Continuous Multimodal Human Action Dataset (C-MHAD), in which video and inertial data stream are captured simultaneously in a continuous way. This dataset is then used in an example recognition technique and the results obtained indicate that the fusion of these two sensing modalities increases the F1 scores compared to using each sensing modality individually.