A Review of Research of Object Detection Area: Current and Future Trends

Abstract

Object Detection is the key ability of computer vision systems to classify and localize objects in images and videos. The methods employed by computer vision systems to perform object detection task is classified into two broad categories i.e. traditional methods and evolutionary methods. The traditional methods of object detection deal with locating few objects in a single image by looking at the features like shape, texture, color, and region. With the emergence of approaches such as Convolutional Neural Networks (CNNs) and Deep Learning, multiple objects can be detected in a large number of images and videos. The methods based on Convolutional Neural Networks (CNNs) and Deep Learning are known as evolutionary methods. The key ability of evolutionary methods is that these can be used for real-time detection and large datasets containing millions of images. In this work, we have presented a review of object detection research focusing on current and future approaches of object detection methods. Further, at the end of this work, we have presented open research problems of object detection. This work provides insight of the development of research in the area of object detection. This work provides a useful information to the keen researchers to carry their research in the object detection area.