Development of Ball Detection System with YOLOv3 in a Humanoid Soccer Robot

One of the practical researches of humanoid robots is research on the use of humanoid robots to play soccer. Research in this field is also encouraged by the existence of various humanoid robot soccer competitions. In humanoid robots for soccer, one of the important aspects is the robot’s ability to detect the ball, goal, field boundaries and other players, both friend players and opposing players. This study focuses on the ball detection system which is a basic ability that humanoid robots need to have. The ball detection system developed in this study uses the YOLOv3 method. The test results show that the system built and trained with 3000 image samples can detect balls at a distance of 50 to 900 cm. The time it takes to detect the ball is about 0.033 seconds.

A large quantity of steel balls automatic precise counting device based on dual sensor auto-correcting method

A large quantity of Steel Balls Automatic precise Counting device is introduced in this paper. Inductance sensors are used for ball detection and STC15F2K60S2 microprocessor is used to do the signal processing. When steel balls are sent to the PVC pipe at the same time, some balls will connect together because of the collision. The sensor will send a connected signal instead of multiple signals if it meets the connected balls. This could cause counting mistake of the device. A correction method is used to solve this problem. The device setup angle could be gotten by using dual sensors to get the average moving speed of the steel balls according to the fixed relations between the setup angle and the speed, which is not affected by whether the steel balls overlap or not because it used two voltage Jump edge to judge the start and end moment of timer. After that, the device setup angle is used to get the standard moving time to single sensor according to the known function relationship. The counting numbers are corrected by using the standard duration to compare with each recording low voltage duration passing single sensor. This method solves the counting mistake problem when a lot of steel balls are pushed into the PVC pipe together. The device improves the efficiency and accuracy of the ball counting.

Ball and Player Detection & Tracking in Soccer Videos Using Improved YOLOV3 Model

Over the past few years, there has been a tremendous increase in the interest and enthusiasm for sports among people. This has led to an increase in the importance given to video recording of various sports that capture even the minutest detail using high-end equipment. Recording and analysis have thereby become extremely crucial in sports like soccer that involve several complex and fast events. Ball detection and tracking along with player analysis have emerged as an area of interest among a lot of analysts and researchers. This is because it helps coaches in performance assessment of the team and in decision making to obtain optimized results. Video analysis can additionally be used by coaches and recruiters to look for new, talented players based on their previously played games. Ball detection also plays a pivotal role in assisting the referees in making decisions at game-changing moments. However, as the ball is almost always moving, its shape-appearance keeps changing over time and it is frequently occluded by players, it makes it difficult to track it throughout the game. We propose a deep learning-based YOLOv3 model for the ball and player detection in broadcast soccer videos. Initially, the videos are processed and unnecessary parts like zoom-ins, replays, etc., are removed to obtain only the relevant frames from each game. Tracking is achieved using the SORT algorithm which employs a Kalman filtering and bounding box overlap.

Improving the speed of ball detection process and obstacle detection process in ERSOW robot using omnidirectional vision based on ROS

This paper presents a novel approach for improving the computation speed of the ball detection and obstacle detection processes in our robot. The conditions of obstacle detection and ball detection in our robot still have a slow processing speed, this condition makes the robot not real-time and the robot's movement is hampered. To build a good world model, things to note are obstacle information and real-time ball detection. The focus of this research is to increase the speed of the process of the ball and obstacle detection around the robot. To increase the speed of the process, it is necessary to optimize the use of the OpenCV library on the robot operating system (ROS) system to divide the process into several small processes so that the work can be optimally divided into threads that have been created. Then, minimize the use of too many frames. This information will be sent to the base station and also for obstacle avoidance purposes.

A New Ball Detection Strategy for Enhancing the Performance of Ball Bees Based on Fuzzy Inference Engine

Sports video analysis has received much attention as it is turned to be a hot research area in the field of image processing. This led to opportunities to develop fascinating applications supported by analysis of different sports especially football. Identifying the ball in soccer images is an essential task for not only goal scoring but also players’ evaluation. However, soccer ball detection suffers from several hurdles such as; occlusions, fast moving objects, shadows, poor lighting, color contrast, and other static background objects. Although several ball detection techniques have been introduced such as; Frame Difference, Mixture of Gaussian (MoG), Optical Flow and etc., ball detection in soccer games is still an open research area. In this paper, a new Fuzzy Based Ball Detection (FB2D) strategy is proposed for identifying the ball through a set of image sequences extracted form a soccer match video. FB2D has the ability to accurately identify the ball even if it is attached to the white lines drawn on the playground or partially occluded behind players. FB2D has been compared to recent ball detection techniques. Experimental results have shown that FB2D outperforms recent detection techniques as it introduced the maximum accuracy and the accuracy of detection in the testing stage is close to 100%. As well as the minimum error.

Size Detection Method of Embedded Ball Based on Aviation Bearing Image

In the aerospace industry, bearing is widely used in various rotating machinery. The performance of bearing affects the operation of the whole machinery and even aviation equipment. The wrongly assembled ball due to size is an important reason for unqualified bearing. To solve this problem, an accurate ball detection method based on the bearing image is proposed. Firstly, according to the imaging characteristics of bearing and light propagation characteristics, an image collection system based on the coaxial light source is designed. Then, aiming at the problem that the embedded ball is occluded by the bearing ring and the cage, only partial ball in the narrow gap can be used to predict the full ball and the high-precision requirement of ball detection, a ball segmentation model based on DeepLab v3+ network is used to segment the local ball, and CBAM is added in the Xception network of the original network. According to the characteristics of the segmentation result, a circle detection algorithm based on circle fitting evaluation designed for incomplete short arc is proposed. Finally, according to the detection results, judge whether the bearing is qualified or not and evaluate the feasibility of this method. Experimental results show that the ball detection accuracy is about 27 microns, and the wrongly assembled ball with a size difference of only 198 microns can be distinguished. The false detection rate of unqualified bearing is 1%. As the last line of defense of bearing quality inspection, this method can achieve zero false detection rate of unqualified bearing in the industry.