Abstract
We propose a deep neural network model that recognizes the position and velocity of a fast-moving object in a video sequence and predicts the object’s future motion. When filming a fast-moving subject using a regular camera rather than a super-high-speed camera, there is often severe motion blur, making it difficult to recognize the exact location and speed of the object in the video. Additionally, because the fast moving object usually moves rapidly out of the camera’s field of view, the number of captured frames used as input for future-motion predictions should be minimized. Our model can capture a short video sequence of two frames with a high-speed moving object as input, use motion blur as additional information to recognize the position and velocity of the object, and predict the video frame containing the future motion of the object. Experiments show that our model has significantly better performance than existing future-frame prediction models in determining the future position and velocity of an object in two physical scenarios where a fast-moving two-dimensional object appears.
Highlights
Through visual observation, humans can perform quick and accurate physical reasoning.Many decisions in everyday life are made based on this physical reasoning ability
FDB1 and FDB2 were composed of 1000 video sequences, and FDB3 was composed of 2800 video sequences
Each video sequence in fast-drifting ball (FDB) dataset was composed of 20 frames of 64 × 64 frames, and each video sequence in fast-thrown ball (FTB) dataset was composed of 10 frames of 160 × 120 frames
Summary
Humans can perform quick and accurate physical reasoning. Many decisions in everyday life are made based on this physical reasoning ability. If we play Jenga, we can infer the stable state of the stacked blocks to determine which block to extract without toppling the tower. If we recognize that a threatening object is rapidly flying towards us, we can move our bodies quickly to avoid collision. For a machine to make similar reasonable judgments and actions to solve problems alongside humans, a considerably fast and accurate physical reasoning capability is required. Research is necessary to help machines make reasonable physical inferences
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.