• VIVITHA V
• M.ANGELSHALINI

Due to the importance of real-time applications such as video surveillance systems, person identification, automated driver assistance, and automotive safety, pedestrian detection is a rapidly growing research area in computer vision. Because pedestrians are vulnerable in heavy traffic, especially in urban areas, pedestrian detection is critical for road safety. In various scenarios for pedestrian detection, the existing techniques of Deformable Part Model, extended deep model, RealBoost method, and Deep Neural Networks have been used. This study presents a method for detecting objects and extracting features from static video imagery that uses color/gray-scale frames captured by common digital cameras or images readily available from external sources. A deep leaning technique is used to segment objects. The supporting hardware is a dedicated P4 PC-based image processing environment, while the intrinsic software was simulated and validated on the MATLAB 2013a platform. We develop a deep leaning algorithm to detach the moving object from the background in this study. The deep leaning algorithm is very efficient and robust, as demonstrated by our experiments. This method could be used in a variety of fields, including vehicle and pedestrian traffic flow measurement, athletic and dancing performance evaluation, public, private, and military security, and so on.

Deep Learning algorithm, pedestrian detection, classification, video processing, MATLAB platform.

"OBJECT DETECTION AND FEATURES EXTRACTION IN VIDEO FRAMES USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.f481-f490, May-2022, Available :http://www.jetir.org/papers/JETIR2205667.pdf

"OBJECT DETECTION AND FEATURES EXTRACTION IN VIDEO FRAMES USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppf481-f490, May-2022, Available at : http://www.jetir.org/papers/JETIR2205667.pdf