厨师服

识别指定区域内标人员穿着黑色或者白色厨师服及其它黑色或者白色衣服，以及是否穿着围裙
精度对应场景或者限制条件
1）图片分辨率：1080p及以上。
2）设备/镜头：支持RGB可见光彩色图像；不支持红外图像。
3）成像条件：画面清晰，无明显拖尾、抖动、异常颗粒、偏色等模糊情况。画面曝光合适，无过曝引起的高光溢出，无强逆光。目标边缘清晰，与背景对比鲜明，肉眼可分辨属性。
4) 算法边界：
遮挡：人体躯干完全不能遮挡。
场景复杂度：单图人数量小于10；
尺寸：以1920*1080分辨率图像为基准，人体目标大于60*140；其他分辨率图像按照相应比例调整目标大小限制

Identify personnel within the specified region who are wearing black or white chef uniforms and other black or white clothing, as well as determine whether they are wearing aprons.

Scenarios and constraints corresponding to the accuracy requirements:
1) Image resolution: 1080p and above.
2) Device/lens: Supports RGB visible light color images; infrared images are not supported.
3) Imaging conditions: The image must be clear, free of obvious smearing, jitter, abnormal grain, color cast and other blurring artifacts. The exposure shall be appropriate, with no highlight overflow caused by overexposure, and no strong backlighting. The edges of the target are distinct, with high contrast against the background, and the attributes can be distinguished by the naked eye.
4) Algorithm boundaries:
Occlusion: The human torso must not be completely occluded.
Scene complexity: The number of people in a single image is less than 10;
Size: Taking a 1920×1080 resolution image as the benchmark, the human target shall be larger than 60×140 pixels; for images of other resolutions, adjust the target size limit proportionally according to the corresponding scale.

搜集汇总

背景与挑战

背景概述

该数据集是一个图像识别算法模型，专注于检测人员是否穿着特定颜色的厨师服和围裙，对输入图像有严格的技术要求。