ABSTRACT
Object detection is a challenging task in computer vision applications that includes person detection, face detection, vehicle detection, pedestrian's detection, and human behavior detection. In conventional object detection methods, the features are extracted using handcrafted algorithms. The main aim of the object detection is to identify the object's location in the images or videos, and also gives the information about class of an objects. But with the different poses of person, occlusions and illumination changes of images, it is very difficult to detect the objects in the images. Due to recent developments in technologies, deep learning methods are used to detect and classify the objects in computer vision applications. In this chapter, we have been presented a survey on object detection algorithms. Various datasets like PASCAL VOC versions, ILSVRC, MS COCO, and Open of object detection (OICOD) provide information. In the experimental analysis, various methods are compared and finally discussed the advantages and disadvantages of the different object detection methods. Finally, many interesting directions are presented for future work in an object detection system.
