Alexandre Alahi

Bio: Alexandre Alahi is an academic researcher. The author has contributed to research in topics: Video capture & Law enforcement. The author has an hindex of 1, co-authored 1 publications receiving 15 citations.

Video Analysis for Body-worn Cameras in Law Enforcement.

Abstract: The social conventions and expectations around the appropriate use of imaging and video has been transformed by the availability of video cameras in our pockets. The impact on law enforcement can easily be seen by watching the nightly news; more and more arrests, interventions, or even routine stops are being caught on cell phones or surveillance video, with both positive and negative consequences. This proliferation of the use of video has led law enforcement to look at the potential benefits of incorporating video capture systematically in their day to day operations. At the same time, recognition of the inevitability of widespread use of video for police operations has caused a rush to deploy all types of cameras, including body worn cameras. However, the vast majority of police agencies have limited experience in utilizing video to its full advantage, and thus do not have the capability to fully realize the value of expanding their video capabilities. In this white paper, we highlight some of the technology needs and challenges of body-worn cameras, and we relate these needs to the relevant state of the art in computer vision and multimedia research. We conclude with a set of recommendations.

Edge Video Analytics for Public Safety: A Review

Abstract: With the installation of enormous public safety and transportation infrastructure cameras, video analytics has come to play an essential part in public safety. Typically, video analytics is to collectively leverage the advanced computer vision (CV) and artificial intelligence (AI) to solve the four-W problem. That is to identify Who has done something (What) at a specific place (Where) at some time (When). According to the difference of latency requirements, video analytics can be applied to postevent retrospective analysis, such as archive management, search, forensic investigation and real-time live video stream analysis, such as situation awareness, alerting, and interested object (criminal suspect/missing vehicle) detection. The latter is characterized as having higher requirements on hardware resources as the sophisticated image processing algorithms under the hood. However, analyzing large-scale live video streams on the Cloud is impractical as the edge solution that conducts the video analytics on (or close to) the camera provides a silvering light. Analyzing live video streams on the edge is not trivial due to the constrained hardware resources on edge. The AI-dominated video analytics requires higher bandwidth, consumes considerable CPU/GPU resources for processing, and demands larger memory for caching. In this paper, we review the applications, algorithms, and solutions that have been proposed recently to facilitate edge video analytics for public safety.

Demo Abstract: EVAPS: Edge Video Analysis for Public Safety

Abstract: Real-time video analysis at the edge of the network is very promising to significantly improve public safety, e.g., dangerous accidents detection and find a missing person. Simply uploading the video stream to the cloud for analysis costs too much energy and network bandwidth to an energy-limited camera. Hence we propose EVAPS (Edge Video Analysis for Public Safety), which distributes the computing workload in both the edge nodes and the cloud in an optimized way. EVPAS is able to eliminate unnecessary data transmission over and save energy for edge devices, i.e., cameras. Three demos are used to illustrate the energy efficiency and optimized solution for public safety using the proposed EVAPS framework.

Body Cameras, Big Data, and Police Accountability

Abstract: The increase in data from police-worn body cameras can illuminate formerly opaque practices. This article discusses using audiovisual big data from police-worn body cameras, citizen recordings, and other sources to address blind spots in police oversight. Based on body camera policies in America's largest cities, it discusses two possible roadblocks: (1) data retention and deletion, and (2) limits on use for evaluation and discipline. Although recordings are retained for criminal prosecutions, retention for oversight and accountability is overlooked or is contentious. Some departments have no policy on videos concerning civil suits against the police. The retention time for non-evidentiary recordings is also much shorter. Some policies limit their use for evaluation and discipline. Transactional myopia—seeing at the case rather than the systemic level—leads to a focus on specific footage for particular cases, rather than the potential of aggregated body camera big data to reveal important systemic information and to prevent the escalation of problems.

Video redaction: a survey and comparison of enabling technologies

Abstract: With the prevalence of video recordings from smart phones, dash cams, body cams, and conventional surveillance cameras, privacy protection has become a major concern, especially in light of legislation such as the Freedom of Information Act. Video redaction is used to obfuscate sensitive and personally identifiable information. Today’s typical workflow involves simple detection, tracking, and manual intervention. Automated methods rely on accurate detection mechanisms being paired with robust tracking methods across the video sequence to ensure the redaction of all sensitive information while minimizing spurious obfuscations. Recent studies have explored the use of convolution neural networks and recurrent neural networks for object detection and tracking. The present paper reviews the redaction problem and compares a few state-of-the-art detection, tracking, and obfuscation methods as they relate to redaction. The comparison introduces an evaluation metric that is specific to video redaction performance. The metric can be evaluated in a manner that allows balancing the penalty for false negatives and false positives according to the needs of particular application, thereby assisting in the selection of component methods and their associated hyperparameters such that the redacted video has fewer frames that require manual review.