A Cognitive Approach To Predict the Multi-

[摘要] Pedestrian detection is one of the important areas in computer vision. This work is about detecting the multi- directional pedestrian’s left, right, and the front movements. On recognizing the direction of movement, the system can be alerteddepending on the environmental circumstances. Since multiple pedestrians moving in different directions may be present in asingle image, Convolutional Neural Network (CNN) is not suitable for recognizing the multi-directional movement of thepedestrians. Moreover, the Faster R-CNN (FR-CNN) gives faster response output compared to other detection algorithms. Inthis work, a modified Faster Recurrent Convolutional Neural Network (MFR-CNN), a cognitive approach is proposed fordetecting the direction of movement of the pedestrians and it can be deployed in real-time. A fine-tuning of the convolutionallayers is performed to extract more information about the image contained in the feature map. The anchors used in the detectionprocess are modified to focus the pedestrians present within a range, which is the major concern for such automated systems.The proposed model reduced the execution time and obtained an accuracy of 88%. The experimental evaluation indicates thatthe proposed novel model can outperform the other methods by tagging each pedestrian individually in the direction in whichthey move.

[学科分类] 计算机科学（综合）

[关键词] Automated driving system;deep neural networks;faster recurrent-convolutional neural network;object recognition;pedestrian detection;pedestrian movement direction