Object detection dataset with soccer balls in different formats: PascalVOC, COCO, CreateML. Train neural network in few clicks. Computer Vision Dataset Store.
Ball detection datasets comprises three diffrent publicly available datasets for soccer, basketball, and volleyball sports. These datasets consist of approximately 34000 frames. They are labeled manually, frame by frame, for the purpose of academic studies in ball detection by the members of Image Processing Laboratory (IPL) of Sharif University of Technology .
More Soccer Ball Dataset images
Drag and drop images into the new project. Create a new "soccer ball" annotation title, and start to label them. By the way, you can import my dataset into your project. Just go to the Dataset Store and select Soccer Ball dataset. So, it looks like we are ready to start training. Training. Now we have 182 annotated images for training.
I found that the dataset better includes many arbitrary positions of the objects. Because soccer ball appears in almost every location in a game, the unseen locations are hard to be predicted. Finally, soccer ball sometimes appears in between players or is hidden partially by players, and it also made algorithm hard to predict.
Soccer Ball Detection using YOLOv2 (Darkflow) Introduction. This notebook shows how object detection can be done on your own dataset by training YOLOv2. I am going to use soccer playing images as training dataset as an example to detect soccer ball.
Data from the paper "Detecting soccer balls with reduced neural networks" This directory contains the results from our JINT 2020 paper, in which we trained multiple MobileNetV2 and V3 as well as YOLO and TinyYOLO v3 and v4 models on a soccer ball image dataset collected from humanoid robots.
This dataset also has a small dataset (manually extracted) of the ball position. The file-names of the repsective video and ball position files have corresponding names, i.e., the video file 0000_2013-11-28 19:03:54.469509000.h264 has 75 video frames, and the corresponding tracing file is named 0000_2013-11-28 19:03:54.469509000.h264_track.txt.
Soccer analytics has attracted interest for a long time 1,2.In the early 1950s Charles Reep collected statistics by hand to suggest that “the key to scoring goals is to transfer the ball as ...