Web-Page Interfaced Real-Time Object Detection Using TensorFlow

Technology has improved fast in recent years. With the development of the powerful microprocessor and good quality camera technologies like artificial intelligence and computer vision making significant strives in modern times. Computer vision-based real-time object detection helps detect, locate, and trace an object from an image or a video with the use of these technologies. This paper proposes a method to interface this real-time system into a web page. To detect objects the TensorFlow object detection API is used and live video is streamed through a password-protected login web page which can be accessed from any device. The system creates a bounding box around the object and also shows the detection accuracy.