CVAT supports the widest variety of computer vision annotation tasks of any tool we have used or evaluated in the years I have worked in computer vision - classification, tracking, object detection, pose, attributes, and more! Gone are the days where we need to design our own labeling tool in-house to support a critical labeling feature. CVAT has multiple deployment paradigms which allow: working on locally in a development environment, deploying for a small team, or even deploying to a large team. It has a large, vibrant, active, responsive, and open community. The project's documentation is extensive and helpful for developers and annotators alike.

Machine learning model structuring and processing is not as easy as it may sound. Without the availability of required data, it is difficult to imagine the accuracy of results. At the core of several AI programs wherein complex computations are done, machine learning algorithms also enable the systematic rendering of learning tasks. As much as the quality of data is central to an algorithm, following the stages of applying the data for performance decides the accuracy of prediction. Whether the data is limited or available in ample amounts, imagining data annotation manually isn't a practical solution when business demands are changing rapidly.

We are using NVIDIA Jetson Nano Developer kit as our accelerator system.Which will contain Docker Container which will contain the dataset and trained model SSD (Single Shot Detector) MobileNetV2 which we will be used to for facial detection. Video would be recorded through the Camera attached to the accelerator system. Code of the SSD (Single Shot Detector) MobileNetV2 is written in Python Programming Language and Deep learning framework which has been used is PyTorch.To optimized the neural network layers.NVIDIA TensorRT is used for faster Inference during the run time.

Cities around the world have an increasing number of inhabitants, and when the number of people in an area increases also the production of garbage is increased. This created the dilemma of collecting this garbage. By making this process more efficient the garbage will be on city streets for a shorter duration and thus have less negative effects on the environment. When garbage can be detected in a timely manner this will allow for a more efficient reaction from the local government, which in turn can deploy the correct resources to solve the problem. For example a truck that can pick up bulky waste or enforcers that can enforce when local regulations are broken.