We propose to create an efficient and less resource-intensive way to loading video data for training and an attempt at creating a viable model that can identify suspicious activities and distinguish them from normal events.

To safely operate in the real world, robots need to evaluate how confident they are about what they see around . A new challenge in computer vision algorithms to not just detect and localize objects, but also report how certain they are. Object detection is often an important part of the perception system of robots or autonomous systems such as driverless cars. It provides crucial information about the robot’s surroundings and has significant influence on the performance of the robot in its environment. For example, driverless cars need object detection to be aware of other cars, pedestrians, cyclists and other obstacles on the road. Future domestic service robots and robots in healthcare will have to be able to detect a large range of household objects in order to properly fulfill their tasks.