Deep Learning in Object Detection: a Review

Abstract

Object detection continues to play a significant part in computer vision theory, study and practical application. Conventional object detection algorithms were primarily derived from machine learning. This involved the design of features for describing the object's characteristics followed by an integration with classifiers. In recent years, the application of deep learning (DL), and more specifically Convolutional Neural Networks (CNN) have elicited a great advancement and promising progress, and has therefore, received much attention on the global stage of research about computer vision. This paper conducts a review about some of the most important and recent developments and contributions that have been made towards research in the use of deep learning in object detection. Moreover, as evidently demonstrated, the findings of numerous studies suggest that the application of deep learning in object detection much surpasses conventional approaches focused on handcrafted and learned features.