Sentence Directed Video Object Codetection

Video object detection is a broad field with many applications ranging from self-driving cars to security surveillance. Video object codetection normally requires the pre-learning of objects before they can be detected. Pre-learning is a problem with many applications given it is not possible to pre-learn all potential scenarios. In addition, most of the work in object detection focuses on still images, which is simpler than the changing and moving viewpoints found in videos.

Researchers at Purdue University have developed a new method of video object codetection using the audio and visual cues in the video to help interpret and detect objects. This technology allows for video object detection without the need for object pre-learning. Using an algorithm that first generates sentences that describe an object's appearance/movement in the video by comparing subtle differences against a static background, it produces and displays a bounding box around an object while it is present in the video field. Using this technology, object detection is more robust, allowing for the detection of more objects, faster, and more accurately than ever before.

Advantages:

-Objects do not need to be pre-learned

-Increased accuracy

-Detects nearly any sized object

-Detects multiple objects simultaneously

-Works with fast object movement and motion blur

Potential Applications:

-Surveillance

-Security

-Autonomous vehicles

-Facial recognition

-Computer vision

-Medical imaging

-Robotics

TRL: 5

Intellectual Property:

Keywords: Video object detection, video object codetection, object pre-learning elimination, audio-visual object detection, bounding box generation, robust object detection, simultaneous object detection, autonomous vehicle object detection, security surveillance object detection, computer vision object detection, Computer Technology, Detection, Machine Learning