Object detection algorithms play a crucial role in other vision tasks. This paper finds that the action recognition algorithm SlowFast’s detection algorithm FasterRCNN (Region Convolutional Neural Network) has disadvantages in terms of both detection accuracy and speed and the traditional IOU (Intersection over Union) localization loss is difficult to make the detection model converge to the minimum stability point. To solve the above problems, the article uses YOLOv3 (You Only Look Once), YOLOX, and CascadeRCNN to improve the detection accuracy and speed of the SlowFast. This paper proposes a new localization loss function that adopts the Lance and Williams distance as a new penalty term. The new loss function is more sensitive when the distance difference is smaller, and this property is very suitable for the late convergence of the detection model. The experiments were conducted on the VOC (Visual Object Classes) dataset and the COCO dataset. In the final videos test, YOLOv3 improved the detection speed by 10.5 s. CascadeRCNN improved by 3.1%AP compared to FasterRCNN in the COCO dataset. YOLOX’s performance on the COCO dataset is also mostly better than that of FasterRCNN. The new LIOU (Lance and Williams Distance Intersection over Union) localization loss function performs better than other loss functions in the VOC dataset. It can be seen that improving the detection algorithm of the SlowFast seems to be crucial and the proposed loss function is indeed effective.

The number system is the representation method of numbers, and number system conversion is the most basic function of a computing system. The decimal system is the most commonly used number system; however, it may not necessarily be the most suitable number system in a computing system. This paper investigates the conversion methods between different number systems and designs corresponding cells, such as P systems, to implement them. The P systems we designed include Π_{10_2} and Π_{2_10} to implement conversion between decimal and binary, Π_{10_m} and Π_{m_10} to implement conversion between decimal and m-base. The operation process of each P system was explained through examples, and their feasibility and effectiveness were verified through simulation software, UPSimulator.

Membrane computing is a branch of natural computing, which is a new computational model abstracted from the study of the function and structure of living biological cells. The study of numerical computation based on membrane computation has received increasing attention in recent years, where maximum parallelism in the execution of evolutionary rules plays an important role in improving the efficiency of numerical computation. Numbers in numerical computation are usually represented as decimals or fractions, and this paper investigates the fundamental problem in fraction representation and operations—fraction simplification. By improving the parallelization of two traditional fractional reduction algorithms, we design the corresponding fractional reduction class cells P System ${\Pi }_1$ and P System ${\Pi }_2$. Combining these two P Systems, this paper designs P System ${\Pi }_3$. The feasibility and effectiveness of the P System designed in this paper are verified experimentally with the simulation software UPSimulator, and the characteristics and application scenarios of the three P Systems are analyzed.