Covid Face-Mask Monitoring Dataset

During the present time, COVID-19 situation is the topmost priority in our life. We are introducing a new dataset named Covid Face-Mask Monitoring Dataset which is based on Bangladesh perspective. We have a main concern to detect people who are using masks or not in the street. Furthermore, few people are not wearing masks properly which is harmful for other people and we have the intention to detect them also. Our proposed dataset contains 6,550 images and those images collected from the walking street, bus stop, street tea stall, foot-over bridge and so on. Among the full dataset, we selected 5,750 images for training purposes and 800 images for validation purposes. Our selected dimension is 1080 × 720 pixels for entire dataset. The percentage of validation data from the full dataset is almost 12.20%. We used a personal cell phone camera, DSLR for collecting frames and adding them into our final dataset. We have also planned to collect images from the mentioned place using an action camera or CCTV surveillance camera. But, from Bangladesh perspective it is not easy to collect clear and relevant data for research. To extend, CCTV surveillance cameras are mostly used in the university, shopping complex, hospital, school, college where using a mask is mandatory. But our goal of research is different. In addition, we want to mention that in our proposed dataset there are three classes which are 1. Mask, 2. No_mask, 3. Mask_not_in_position.

当前，新冠疫情（COVID-19）仍是我们生活中的头等要务。本次我们推出一款基于孟加拉国视角构建的新冠口罩佩戴监测数据集（Covid Face-Mask Monitoring Dataset）。本数据集的核心目标为识别街道场景中佩戴口罩与未佩戴口罩的人群；此外，部分人群未正确佩戴口罩，此举会对他人健康造成危害，我们同样希望能够识别此类人群。本数据集共包含6550张图像，采集自步行街、公交站点、街边茶摊、人行天桥等多种场景。在全数据集中，我们选取了5750张图像用于训练、800张图像用于验证，验证集占全数据集的比例约为12.20%。本数据集所有图像的统一分辨率为1080×720像素。图像采集设备包括个人手机与数码单反相机（DSLR），采集的帧数据均被纳入最终数据集。我们原计划还将使用运动相机或闭路电视监控摄像头（CCTV）在上述场景中采集图像，但从孟加拉国的实际情况来看，获取清晰且符合研究需求的数据并非易事。进一步而言，闭路电视监控摄像头多部署于大学、购物中心、医院、中小学及高等院校等强制要求佩戴口罩的场所，但本研究的目标场景与此类场所不同。此外，本数据集共包含三个类别：1. 正确佩戴口罩（Mask）；2. 未佩戴口罩（No_mask）；3. 口罩佩戴位置不当（Mask_not_in_position）。