Case Study: PPE Assessment
We trained a neural network to assess PPE compliance in CCTV images and videos. Fine grained image properties can be extracted, and statistics can be tracked and stored. This model can be trained to detect specific types of objects and features, according to client's needs.
Evaluating your Images
You can find below a list of your pictures, ranked according to the number of PPE scoped objects that were detected within them, such as helmets and goggles. The image on top is the most likely to contain PPE related entities according to our pretrained models. All the way to the image at the bottom of the list, which shows the least amount of detected objects. Try uploading more pictures, and see the list updating accordingly!