Underwater Accompanying Robot Based on SSDLite Gesture Recognition

Abstract

Underwater robots are often used in marine exploration and development to assist divers in underwater tasks. However, the underwater robots on the market have some problems, such as only a single function of object detection or tracking, the use of traditional algorithms with low accuracy and robustness, and the lack of effective interaction with divers. To this end, we designed a type of gesture recognition based on interaction, using person tracking as an auxiliary means for an underwater accompanying robot (UAR). We train and test the SSDLite detection algorithm using the self-labeled underwater datasets, and combine the kernelized correlation filters (KCF) tracking algorithm with the “Active Control” target tracking rule to continuously track the underwater human body. Our experiments show that the use of underwater datasets and target tracking can effectively improve gesture recognition accuracy by 40–105%. In the outfield experiment, the performance of the algorithm was good. It achieved target tracking and gesture recognition at 29.4 FPS on Jetson Xavier NX, and the UAR made corresponding actions according to the diver gesture command.

RETRACTED: Research on motion and attitude control of unmanned underwater platform

“…Due to the richness of mineral resources in the sea, deep-water exploration and marine resource development have been researched in various countries, promoting underwater robot development effectively [1][2][3]. The unmanned underwater platform, as a kind of underwater robot, can carry a variety of equipment to accomplish tasks under harsh subsea conditions and return images in real-time [4,5].…”

SSDLiteX: Enhancing SSDLite for Small Object Detection

“…A CNN for object detection is usually constructed by adding some auxiliary layers to a base CNN for image classification. There are various kinds of object detection CNNs, and widely used for resource-limited systems is the combination of MobileNet V2 and SSDLite [12,[14][15][16]. The network shows an appropriate detection capability with low complexity, but its performance is sometimes not so satisfactory, especially in detecting small objects.…”