Probabilistic collision estimation for tracked vehicles based on corner point self-activation approach. (March 2019)

• Record Type: Journal Article
• Authors: Sathiya, P.; Anandhakumar, P.
• Is Part Of: Computers & electrical engineering. Volume 74(2019)
• Page Start: 557
• Page End: 568
• Publication Date: 2019-03
• Subjects: Unmanned tracked vehicles -- Feature extraction method -- Collision avoidance -- Corner point method -- Time of collision -- Trajectory matrix; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.07.029
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Detection and tracking of Manned-Unmanned Tracked Vehicles (MUTV) have a great demand in defense surveillance applications. This research paper mainly focuses on developing a Corner Point Self-activating Threshold Tuning (CSTT) feature extraction method to locate the position of MUTV. The Collision avoidance system has been recognized as a smart secured system for handling critical scenarios. The Exponential Probability based Collision Avoidance (EPCA) technique has been proposed for estimating the Time of Collision (TOC) between multiple vehicles. The EPCA is structured using a continuous probability distribution to compute the inter-arrival time between the two consecutive arrivals of MUTV. The proposed CSTT feature extraction method was able to detect the MUTV for YouTube dataset with the detection rate of 13.53 s when compared to the existing Harris feature extraction technique of 17.019 s. The system measures the relative speed and distance between the MUTV vehicles towards the critical zone. Many of the existing collision avoidance systems track vehicles in the unidirectional path. Our proposed EPCA system track vehicles from the tri-directional route. Experimental results show that the proposed system can avoid the interaction between the objects/vehicles before the collision occurs.