Active Pedestrian Safety by Automatic Braking and Evasive Steering

Abstract

Abstract-Active safety systems hold great potential to reduce the accident frequency and severity, by warning the driver and/or exerting automatic vehicle control ahead of crashes. This paper presents a novel active pedestrian safety system, which combines sensing, situation analysis, decision making and vehicle control. The sensing component is based on stereo vision; it fuses two complementary approaches for added robustness: motion-based object detection and pedestrian recognition. The highlight of the system is the ability to decide within a split second whether to perform automatic braking or evasive steering, and to execute this maneuver reliably, at relatively high vehicle speeds (up to 50 km/h).We performed extensive pre-crash experiments with the system on the test track (22 scenarios with real pedestrians and a dummy). We obtained a significant benefit in detection performance and improved lateral velocity estimation by the fusion of motion-based object detection and pedestrian recognition. On a fully reproducible scenario subset, involving the dummy entering laterally into the vehicle path from behind an occlusion, the system executed in over 40 trials the intended vehicle action: automatic braking (if a full stop is still possible) or else, automatic evasive steering.

Automatic Human Activity Segmentation and Labeling in RGBD Videos

“…Manual analysis of video is labour intensive, fatiguing, and error prone. Solving the problem of recognizing human activities from video can lead to improvements in several application fields like surveillance systems, human computer interfaces, sports video analysis, digital shopping assistants, video retrieval, gaming and health-care [15,13,8,10]. Ultimately, we are interested in recognizing high-level human activities and interactions between humans and objects.…”

Internet of Things: Architecture, Security and Applications

“…Companies like Apple and Google are moving ahead with autonomous or driverless cars using IoT in transportation. These driverless cars have the ability to autonomously detect as well as differentiate between pedestrian traffic and vehicular traffic in addition to taking evasive steering actions to avoid collisions when needed [36] [37]. These cars can even undertake journeys through preprogrammed routes and also provide emergency assistance whenever required.…”

“…Currently, these autonomous cars are in the rigorous testing stage and within the close future, we will be seeing these cars in most of the major cities throughout the world. Security and protection of privacy are the two major areas of concern that need to be handled before use of IoT is widespread in the transportation as well as logistics industry since most of the vehicle drivers are concerned about privacy invasion and information leak [38]. An effort in law, and regulation, as well as technology, is needed to thwart unauthorized access, disclosure of private data.…”

Connectivity Management of a Pedestrian Smartphone App in the Cyber-Physical Intersection Systems (CPIS)

“…1 기존 연구에서 이러한 문제를 해결하기 위한 방안으 로 교차로 구조설계 기술과 수동형/능동형 자동차 안 전 기술이 제안되었다 [3][4][5] . 또한, Vehicle-to-Everything (V2X) 통신 기반의 교차로 안전 시스템을 위한 다양 한 응용 서비스들을 제시하였다 [6] .…”