Abstract. In recent years, with the advancement of marine resources and environment research, the ecological functions of reef-building coral reef ecosystems distributed in warm shallow waters of the ocean are being continuously discovered and valued by people. It is important for ecosystem protection to monitor the population of marine animals. Besides, many projects of Autonomous Underwater Vehicle (AUV) also need technology to perceive and understand environment information in real-time for better decision-making. Therefore, marine animal detection has become a challenge for researchers to study nowadays. Deep neural network models have been used to solve fish-related tasks and gained encouraging achievements, but there are still many problems in this field. In this paper, several YOLO-based methods are chosen for comparison. Experiment results indicate that these methods can recognize the marine animals in coral reef quickly and accurately. Finally, several recommendations for model improvement according to assessment results are presented.

Abstract. RGB-D cameras are novel sensing systems that can rapidly provide accurate depth information for 3D perception, among which the type based on active stereo vision has been widely used. However, there are some problems exiting in use, such as the short measurement range and incomplete depth maps. This paper presents a robust and efficient matching algorithm based on semi-global matching to obtain more complete and accurate depth maps in real time. Considering characteristics of captured infrared speckle images, the Gaussian filter is performed firstly to restrain noise and enhance the relativity. It also adopts the idea of block matching for reliability, and a dynamic threshold selection of the block size is used to adapt to various situation. Moreover, several optimizations are applied to improve precision and reduce error. Through experiments on the Intel Realsense R200, the excellent capability of our proposed method is verified.