Object Detection, Classification and Counting for Analysis of Visual Events

Abstract

The detection, classification and counting of the object (vehicle) and persons (pedestrians) in the visual event are the crucial tasks of event analysis. Two object classification systems are reported here: (i) the Fast Region-proposal Convolutional Neural Network with hyper-parameter optimization and (ii) “You Only Look Once” (YOLO). The YOLO object detection method shows improvement in the accuracy of categorizing the vehicles and persons in the video input. High-performance Video Transmission (HpVT) protocol, visual IoT device is applied for grabbing the smooth video streams in real-time. Person (pedestrian)and six classes of vehicle types in a relevant environment are detected. These types are Motorbikes, Bicycle, Bus, Truck, Van and Saloon. New object dataset collected and organized person and vehicle images from several internet websites as 5000 images. The feature extraction and segmentation are performed from the images obtained by video streaming camera. The proposed object detection, classification and counting system will provide to the application of smart tracking, smart trip planning, smart surveillance, smart tourism and pedestrian safety monitoring.