Biblio

Video analytics has many applications in traffic control, security monitoring, action/event analysis, etc. With the adoption of deep neural networks, the accuracy of video analytics in video streams has been greatly improved. However, deep neural networks for performing video analytics are compute-intensive. In order to reduce processing time, many systems switch to the lower frame rate or resolution. State-of-the-art switching approaches adjust configurations by profiling video clips on a large configuration space. Multiple configurations are tested periodically and the cheapest one with a desired accuracy is adopted. In this paper, we propose a method that adapts the configuration by analyzing past video analytics results instead of profiling candidate configurations. Our method adopts a lower/higher resolution or frame rate when objects move slow/fast. We train a model that automatically selects the best configuration. We evaluate our method with two real-world video analytics applications: traffic tracking and pose estimation. Compared to the periodic profiling method, our method achieves 3%-12% higher accuracy with the same resource cost and 8-17x faster with comparable accuracy.

This paper explores an innovative approach to the telerobotics reasoning architecture and networking, which offer a reliable and adaptable operational process for complex tasks. There are many operational challenges in the remote control for manufacturing that can be introduced by the network communications and Iatency. A new protocol, named compact Reliable UDP (compact-RUDP), has been developed to combine both data channelling and media streaming for robot teleoperation. The original approach ensures connection reliability by implementing a TCP-like sliding window with UDP packets. The protocol provides multiple features including data security, link status monitoring, bandwidth control, asynchronous file transfer and prioritizing transfer of data packets. Experiments were conducted on a 5DOF robotic arm where a cutting tool was mounted at its distal end. A light sensor was used to guide the robot movements, and a camera device to provide a video stream of the operation. The data communication reliability is evaluated using Round-Trip Time (RTT), and advanced robot path planning for distributed decision making between endpoints. The results show 88% correlation between the remotely and locally operated robots. The file transfers and video streaming were performed with no data loss or corruption on the control commands and data feedback packets.

In recent years, developments in the field of computer vision have allowed deep learning-based techniques to surpass human-level performance. However, these advances have also culminated in the advent of adversarial machine learning techniques, capable of launching targeted image captioning attacks that easily fool deep learning models. Although attacks in the image domain are well studied, little work has been done in the video domain. In this paper, we show it is possible to extend prior attacks in the image domain to the video captioning task, without heavily affecting the video's playback quality. We demonstrate our attack against a state-of-the-art video captioning model, by extending a prior image captioning attack known as Show and Fool. To the best of our knowledge, this is the first successful method for targeted attacks against a video captioning model, which is able to inject 'subliminal' perturbations into the video stream, and force the model to output a chosen caption with up to 0.981 cosine similarity, achieving near-perfect similarity to chosen target captions.

The world is witnessing a remarkable increase in the usage of video surveillance systems. Besides fulfilling an imperative security and safety purpose, it also contributes towards operations monitoring, hazard detection and facility management in industry/smart factory settings. Most existing surveillance techniques use hand-crafted features analyzed using standard machine learning pipelines for action recognition and event detection. A key shortcoming of such techniques is the inability to learn from unlabeled video streams. The entire video stream is unlabeled when the requirement is to detect irregular, unforeseen and abnormal behaviors, anomalies. Recent developments in intelligent high-level video analysis have been successful in identifying individual elements in a video frame. However, the detection of anomalies in an entire video feed requires incremental and unsupervised machine learning. This paper presents a novel approach that incorporates high-level video analysis outcomes with incremental knowledge acquisition and self-learning for autonomous video surveillance. The proposed approach is capable of detecting changes that occur over time and separating irregularities from re-occurrences, without the prerequisite of a labeled dataset. We demonstrate the proposed approach using a benchmark video dataset and the results confirm its validity and usability for autonomous video surveillance.