A Review on the Performance of Object Detection Algorithm

Abstract

This paper represents multiple Object recognitions technology in the field of computer vision for finding and identifying multiple objects in a image or video sequence.It is basically highlight only those objects which are needed. Algorithmic descriptions of recognition task are implemented on machines which is an complex job. Thus multiple object recognition techniques need to be developed which are less intricate and well-organized The multiple object detection is a very important application of image processing. the literature survey has shown that the most of existing methods have ignored the poor quality images like image with noise or poor intensity . Noise means those signals which are not required .Also the most of the existing work for multiple object detection has neglected the use of hybrid technique. The overall goal of this research work is to propose an efficient and simple multiple object detection using the fuzzy and transition region based image segmentation.

Single Camera Object Detection for Self-Driving Vehicle: A Review

“…A well-organized object recognition technique is very helpful in the ways of possessing a good algorithm (Kaur & Marwaha, 2017). In the application of image processing, multi-object detection is considered very important.…”

“…Figure 4: Lane and boundary detection results on straight road, curve road, and unstructured road in various illumination variations For a vehicle behaviour prediction using HD Canon camera, Wang et al (2016) stated the maximum pixels error achieved was 0.585 which clearly showed that his system was reliable, efficient and the most important was much cheaper. Move to the feature extraction of camera based application, a review byKaur and Marwaha (2017), stated that when no remarkable changes on the grey levels between foreground and background, threshold determination image cannot produce an efficient results. On the other hand, the IPM approach used byAly (2014) showed 96.34% correct detection for 2-lane mode and 90.89% correct detection for all-lanes mode.…”