surawut/chess-pieces-dataset-yolo
收藏Hugging Face2025-12-09 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/surawut/chess-pieces-dataset-yolo
下载链接
链接失效反馈官方服务:
资源简介:
---
language:
- en
license: cc-by-4.0
task_categories:
- object-detection
tags:
- chess
- chess-pieces
- yolo
- object-detection
- warped-view
size_categories:
- 1K<n<10K
pretty_name: Chess Pieces Detection Dataset
---
# Chess Pieces Detection Dataset (Warped View) ♟️🔍
## 1. Dataset Description
This dataset contains images of chess pieces taken from a **Top-Down (Warped)** perspective. It is designed for **Object Detection** models (YOLO) to recognize chess pieces and hands on a standardized 640x640 grid.
It is intended to be used as **Phase 2** of a Chess Move Tracking pipeline, receiving input from the Phase 1 Perspective Warper.
- **Task:** Object Detection
- **Format:** YOLOv8 / YOLO11 Detection Format
- **Input:** Warped/Rectified chessboard images (640x640)
- **Classes:** 13 Classes (12 Pieces + Hand)
## 2. Dataset Composition
The dataset includes diverse scenarios to ensure robustness:
1. **Standard Gameplay:** Frames extracted from real gameplay videos.
2. **Occlusions:** Frames where hands are covering pieces (labeled as `Hand`).
3. **Negative Samples:** Empty chessboards (only background) to reduce false positives (~10% of dataset).
4. **Lighting Variations:** Augmented brightness and exposure to simulate different environments.
## 3. Classes
The dataset uses the following class mapping:
| ID | Class Name | Description |
| :--- | :--- | :--- |
| 0 | `Hand` | Human Hand |
| 1 | `bB` | Black Bishop |
| 2 | `bK` | Black King |
| 3 | `bN` | Black Knight |
| 4 | `bP` | Black Pawn |
| 5 | `bQ` | Black Queen |
| 6 | `bR` | Black Rook |
| 7 | `wB` | White Bishop |
| 8 | `wK` | White King |
| 9 | `wN` | White Knight |
| 10 | `wP` | White Pawn |
| 11 | `wQ` | White Queen |
| 12 | `wR` | White Rook |
语言:英语
许可证:知识共享署名4.0(CC BY 4.0)
任务类别:目标检测(Object Detection)
标签:国际象棋、国际象棋棋子、YOLO(You Only Look Once)、目标检测、畸变俯视视角
样本量范围:1000 < 样本量 < 10000
规范名称:棋盘棋子检测数据集(Chess Pieces Detection Dataset)
# 棋盘棋子检测数据集(畸变俯视视角)♟️🔍
## 1. 数据集说明
本数据集包含**俯视(Top-Down, Warped)**视角下拍摄的国际象棋棋子图像,专为目标检测模型(如YOLO)设计,用于在标准化640×640网格上识别国际象棋棋子与手部区域。
本数据集旨在作为国际象棋走棋追踪流水线的**第二阶段(Phase 2)**,接收来自第一阶段透视畸变校正器(Perspective Warper)的输入数据。
- **任务类型:** 目标检测
- **标注格式:** YOLOv8 / YOLO11 检测格式
- **输入数据:** 畸变校正后的棋盘图像(分辨率640×640)
- **类别总数:** 13类(12种棋子 + 手部)
## 2. 数据集构成
为保证模型鲁棒性,本数据集涵盖多样化场景:
1. **标准对局场景:** 从真实对局视频中提取的帧画面
2. **遮挡场景:** 手部遮挡棋子的帧(标注为`Hand`)
3. **负样本:** 仅包含背景的空棋盘图像,用于降低误报率,约占数据集总量的10%
4. **光照变化场景:** 通过调整亮度与曝光度进行数据增强,模拟不同环境光照条件
## 3. 类别映射表
本数据集采用如下类别映射规则:
| 序号 | 类别名称 | 类别描述 |
| :--- | :--- | :--- |
| 0 | `Hand` | 人类手部 |
| 1 | `bB` | 黑方象 |
| 2 | `bK` | 黑方王 |
| 3 | `bN` | 黑方马 |
| 4 | `bP` | 黑方兵 |
| 5 | `bQ` | 黑方后 |
| 6 | `bR` | 黑方车 |
| 7 | `wB` | 白方象 |
| 8 | `wK` | 白方王 |
| 9 | `wN` | 白方马 |
| 10 | `wP` | 白方兵 |
| 11 | `wQ` | 白方后 |
| 12 | `wR` | 白方车 |
提供机构:
surawut



