Application of Smart Sensor in Underwater Weak Object Detection and Positioning

This paper is aimed at studying underwater object detection and positioning. Objects are detected and positioned through an underwater scene segmentation-based weak object detection algorithm and underwater positioning technology based on the three-dimensional (3D) omnidirectional magnetic induction smart sensor. The proposed weak object detection involves a predesigned U-shaped network- (U-Net-) architectured image segmentation network, which has been improved before application. The key factor of underwater positioning technology based on 3D omnidirectional magnetic induction is the magnetic induction intensity. The results show that the image-enhanced object detection method improves the accuracy of Yellow Croaker, Goldfish, and Mandarin Fish by 3.2%, 1.5%, and 1.6%, respectively. In terms of sensor positioning technology, under the positioning Signal-to-Noise Ratio (SNR) of 15 dB and 20 dB, the curve trends of actual distance and positioning distance are consistent, while SNR = 10 dB , the two curves deviate greatly. The research conclusions read as follows: an underwater scene segmentation-based weak object detection method is proposed for invalid underwater object samples from poor labeling, which can effectively segment the background from underwater objects, remove the negative impact of invalid samples, and improve the precision of weak object detection. The positioning model based on a 3D coil magnetic induction sensor can obtain more accurate positioning coordinates. The effectiveness of 3D omnidirectional magnetic induction coil underwater positioning technology is verified by simulation experiments.

A Real-Time FPGA Accelerator Based on Winograd Algorithm for Underwater Object Detection

Real-time object detection is a challenging but crucial task for autonomous underwater vehicles because of the complex underwater imaging environment. Resulted by suspended particles scattering and wavelength-dependent light attenuation, underwater images are always hazy and color-distorted. To overcome the difficulties caused by these problems to underwater object detection, an end-to-end CNN network combined U-Net and MobileNetV3-SSDLite is proposed. Furthermore, the FPGA implementation of various convolution in the proposed network is optimized based on the Winograd algorithm. An efficient upsampling engine is presented, and the FPGA implementation of squeeze-and-excitation module in MobileNetV3 is optimized. The accelerator is implemented on a Zynq XC7Z045 device running at 150 MHz and achieves 23.68 frames per second (fps) and 33.14 fps when using MobileNetV3-Large and MobileNetV3-Small as the feature extractor. Compared to CPU, our accelerator achieves 7.5×–8.7× speedup and 52×–60× energy efficiency.

Lightweight Underwater Object Detection Based on YOLO v4 and Multi-Scale Attentional Feature Fusion

A challenging and attractive task in computer vision is underwater object detection. Although object detection techniques have achieved good performance in general datasets, problems of low visibility and color bias in the complex underwater environment have led to generally poor image quality; besides this, problems with small targets and target aggregation have led to less extractable information, which makes it difficult to achieve satisfactory results. In past research of underwater object detection based on deep learning, most studies have mainly focused on improving detection accuracy by using large networks; the problem of marine underwater lightweight object detection has rarely gotten attention, which has resulted in a large model size and slow detection speed; as such the application of object detection technologies under marine environments needs better real-time and lightweight performance. In view of this, a lightweight underwater object detection method based on the MobileNet v2, You Only Look Once (YOLO) v4 algorithm and attentional feature fusion has been proposed to address this problem, to produce a harmonious balance between accuracy and speediness for target detection in marine environments. In our work, a combination of MobileNet v2 and depth-wise separable convolution is proposed to reduce the number of model parameters and the size of the model. The Modified Attentional Feature Fusion (AFFM) module aims to better fuse semantic and scale-inconsistent features and to improve accuracy. Experiments indicate that the proposed method obtained a mean average precision (mAP) of 81.67% and 92.65% on the PASCAL VOC dataset and the brackish dataset, respectively, and reached a processing speed of 44.22 frame per second (FPS) on the brackish dataset. Moreover, the number of model parameters and the model size were compressed to 16.76% and 19.53% of YOLO v4, respectively, which achieved a good tradeoff between time and accuracy for underwater object detection.

OPTIMIZATION OF THE LENGTH OF THE TOWING CABLE IN THE OPERATIONAL MAGNETOMETRIC SEARCH OF UNDERWATER OBJECTS

One of the features of the creation of a new generation of marine magnetometry means is the requirement to increase the efficiency of the search for emergency underwater objects due to a reasonable reduction in the length of the magnetometer towing cable, which ensures a decrease in the length of the search tack. Traditionally, the length of the cablerope of a towed magnetometer is determined taking into account its sensitivity, as well as the magnetic characteristics of the vessel-tug and underwater object. At the same time, the stochastic nature of the search process is ignored, caused by random factors (the uncertain spatial position of the underwater object in the search strip, as well as the orientation noise of the measuring platform). A new approach to the algorithm for processing the statistical information of the magnetometric signals of the underwater object and the towing vehicle in the search bar makes it possible to determine the optimal length of the towing cable. In this case, the problem of minimizing the objective function of the dependence of two alternatives is solved: on the one hand, a decrease in the towing noise as the tow cable length increases, on the other, an increase in the orientation noise caused by the spatio-temporal oscillations of the magnetometer. In addition, the evaluation of the selection of the signal of the underwater object against the background of the towing vehicle interference in terms of the "statistical discrepancy of alternative hypotheses" – the Kullback divergence, makes it possible to optimize the length of the cable-rope with the given probabilistic values of the detection of the underwater object.