• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.318-325
• /
• 2003

The new biotelemetry method and system that the installation and the treatment of equipment is convenient and the instantaneously detailed position of the fish attached the pinger is able to track comparatively easily had been developed, an availabilities of it were verified in water tank by using hydrophone and pinger. First of all, the receiving system for biotelemetry was calibrated so as to measure tracking of high precision or wide detection range. In the next place, the precision at narrow and wide beam array of receiving system by using hydrophone was investigated and the actual position was compared with measured hydrophone position. The mean standard deviations of the position by narrow beam array of receiving system were 6.4em in phase beam of fore-aft pair and 6.3em in starboard-port pair, and the wide beam array were 24em and 23em respectively. The precision of distance, position, and velocity at narrow beam array of receiving system by using pinger were investigated and the actual values were compared with measured values. The distance from receiving system to pinger was measured by the pinger synchronizing method, angle of direction of pinger was detected by the super short base line (SSBL) method. The three dimensional position of pinger to the receiving system was measured by combining of two kinds of methods (SPB method), the velocity of pinger was obtained with a differential of the three dimensional positions. The mean standard deviations of the distance by pinger synchronizing method in narrow beam array of receiving system was 1. 8 em, that of the position by SPB method was 7.7cm.