Research advanced in object detection based on deep learning

Abstract

In the field of computer vision, identifying specific objects in images and predicting their location and class have long been hot research topics.Algorithms for early object detection rely on traditional handcrafted features, and the speed and precision of their detection cannot meet the needs of real-world applications. Rapid development in convolutional neural networks has accelerated the development of object identification systems based on deep learning.Existing deep learning-based object identification algorithms mostly use two-stage detection and single-stage detection, according to various detection frameworks. In this paper, around the above two types of frameworks, the latest research progress in the field of object detection is systematically introduced. Specifically, we first introduce representative object detection algorithms, including their design ideas, basic processes, and advantages and disadvantages. Second, using widely-used datasets, we objectively compare the effectiveness of several detection techniques. Finally, we summarize the unsolved problems in the detection of objects and talk about the route this topic will take going forward.