Object Detection Performance: A Comparative Study

Abstract

Object detection is a critical task in computer vision with applications in many domains. Recent advances in deep learning have led to significant improvements in the performance of object detectors. This paper presents a comparative performance analysis of generic object detectors, with a focus on single-stage and two-stage detectors. The paper first discusses the taxonomy of object detection algorithms, and then presents a detailed performance comparison of single-stage and two-stage detectors. The performance of different detectors was evaluated on two different datasets, Microsoft COCO and PASCAL VOC 2012. The results showed that DetectoRS is a state-of-the-art two-stage object detector, outperforms all other two-stage models. While YOLOv4 and FCOS are the two most accurate single-stage detectors. The comparative results also show that single-stage detectors are generally less accurate than two-stage detectors, but they are typically faster. The paper also includes the strengths and weaknesses of different object detection approaches and identifies promising directions for future research.

Deep learning approach for a machine-human interface based on optical real-time gesture recognition for automated guided vehicles

“…The research demonstrated that YOLOv4 had attained the highest mAP and inference speed. The research study concluded with the evaluation of YOLOv4[20].…”

Comparative Analysis of Yolo and SSD

“…This is because SSD put regression idea of YOLO and the anchor mechanism of Fast-RCNN in one model and uses multi-scale regions in different positions of the image for regression [20]. The higher resolution layers in the architecture of SSD are responsible for detecting small objects but such layers have some insignificant features which are not useful and are less informative for object detection [4].…”

“…The purpose of object detection is to identify the object in the picture and use the bounding box to locate the object. With the development of deep learning and the needs of the monitoring field, the object detection technology has made great progress [2].It has recently received a great deal of attention due to its wide range of applications, such as self-driving cars, video surveillance, and medical imaging [3].Object detection techniques aim to localize and classify objects in each image that run through the CNN [4].Object detection based on deep learning can be divided into two categories according to detection methods: Region-based and regressionbased. The object detection techniques that are used in our paper are single stage models such as -YOLOv7, YOLOv8 and SSD.…”