Object Detection based on Light Field Imaging

Abstract

Improving the object confidence score of an image using the machine intelligence method is one of the critical objectives for object detection. In this paper, we propose an end-to-end framework to object detection based on light field (LF) imaging. First, we apply refocusing technology to enhance the visual feature expression between different objects in LF images. then, we combine the LF refocusing technology with the efficient darknet53 feature extraction network and multi-feature fusion method, which ensures effectiveness in improving the confidence score of the object in the image. To evaluate the framework, we use a light field camera (LFC) to construct a new real LF image detection dataset, which consists of as many as 20 kinds of common objects (person, car, etc.). Compared with the popular methods, the confidence score achieved by our method shows an improvement for the detection of any single object. Specifically, for the detection of cars and people, the confidence score is increased by 0.03 and 0.02, respectively. For the detection of bicycles, the confidence score significantly improves by 0.27. To some extent our method can also solve the problem of object missed and false detection.