Design Strategy for Identification and Tracking of Video Objects Over Crowded Video Scenes using a Novel Feature-Learning Algorithm

The idea of tracking video objects has evolved to facilitate the area of surveillance systems. It is mainly observed that the existing video tracking models are more inclined towards improving the accuracy where the consideration of a more significant proportion of mobile objects dynamics in motion over the crowded video frame sequence is mainly overlooked, which is essential to study a specific movement pattern of mobile objects appearing in the video frame sequence. Moreover, research solutions mostly need more effectiveness when it comes to the cost of computation. The study thereby introduces a unique, simplified video tracking strategy capable of assessing a specific pattern of mobile objects movement over complex and crowded video scenes. The research findings show that, unlike the existing system, the proposed tracking model attains approximately 11.4523% improvement over the precision score and 0.882202 % over the F1 measure while reducing the feature computation time to 0.128124 sec.