Due to the importance of underwater exploration in the development and utilization of deep-sea resources, underwater autonomous operation is more and more important to avoid the dangerous high-pressure deep-sea environment. For underwater autonomous operation, the intelligent computer vision is the most important technology. In an underwater environment, weak illumination and low-quality image enhancement, as a preprocessing procedure, is necessary for underwater vision. In this paper, a combination of max-RGB method and shades of gray method is applied to achieve the enhancement of underwater vision, and then a CNN (Convolutional Neutral Network) method for solving the weakly illuminated problem for underwater images is proposed to train the mapping relationship to obtain the illumination map. After the image processing, a deep CNN method is proposed to perform the underwater detection and classification, according to the characteristics of underwater vision, two improved schemes are applied to modify the deep CNN structure. In the first scheme, a 1∗1 convolution kernel is used on the 26∗26 feature map, and then a downsampling layer is added to resize the output to equal 13∗13. In the second scheme, a downsampling layer is added firstly, and then the convolution layer is inserted in the network, the result is combined with the last output to achieve the detection. Through comparison with the Fast RCNN, Faster RCNN, and the original YOLO V3, scheme 2 is verified to be better in detecting underwater objects. The detection speed is about 50 FPS (Frames per Second), and mAP (mean Average Precision) is about 90%. The program is applied in an underwater robot; the real-time detection results show that the detection and classification are accurate and fast enough to assist the robot to achieve underwater working operation.

Seabed fishing depends on humans in common, for instance, the sea cucumber, sea urchin, and scallop fishing, which is always a very dangerous task. Considering the underwater complex environment conditions such as low temperature, dim vision, and high pressure, collecting the marine products using underwater robots is commonly regarded as a feasible solution. The key technique of the underwater robot development is to detect and locate the main target from underwater vision. This research is based on the deep convolutional neural network (CNN) to realize the target recognition from underwater vision. The RPN (Region Proposal Network) is used to optimize the feature extraction capability. Deep learning dataset is prepared using an underwater video obtained from a sea cucumber fishing ROV (Remote Operated Vehicle). The inspiration of the network structure and the improvements come from the Faster RCNN and Hypernet method, and for the underwater dataset, the method proposed in this paper shows a good performance of recall and object detection accuracy. The detection runs with a speed of 17 fps on a GPU, which is applicable to be used for real-time processing.

Hierarchical scheduling allows the use of different schedulers and provides temporal isolation for different applications on a single hardware platform. We propose a hierarchical scheduling interface called synchronized deferrable servers. In addition to the common advantages of hierarchical scheduling, synchronized deferrable servers can combine partitioned and global multiprocessor scheduling in one system, and increase the schedulable system utilization. Response time analysis of tasks executed by these servers is presented and evaluated through simulation. We show that evenly allocating bandwidth across cores is "better" than other allocation schemes in terms of a task set's schedulability. In addition, under hierarchical scheduling, the threshold between lightweight and heavyweight tasks may be different from what they are under dedicated scheduling.

No abstract

We propose an optimization-based counterflow model to simultaneously investigate the pedestrian lane formation and overtaking behaviour in a heterogeneous bidirectional pedestrian flow. A comparison of pedestrian flow patterns in bidirectional flows with overtaking behaviour between the proposed model and a counterflow-based active decision model is performed with real collected data. Furthermore, the fundamental diagram of heterogeneous pedestrian counterflows with different corridor widths is compared with the experimental data. The effects of personal preferences regarding evading behaviour, going straight ahead and the right-hand traffic norm on lane formation are also studied for different corridor geometries with various pedestrian densities. The numerical results show that both overtaking behaviour in sparse bidirectional crowds and personal preference for the right-hand traffic norm in a wide corridor may reduce the specific flow of a pedestrian counterflow. Simultaneously, a strong personal preference for the right-hand traffic norm can determine lane formation in a counterflow scenario regardless of differences in corridor widths, pedestrian densities or other personal preferences. Additionally, lane formation may enhance not only the traffic efficiency of the whole counterflow but also the mobility of fast pedestrians in a heterogeneous bidirectional pedestrian flow.