Future-Frame Prediction for Fast-Moving Objects with Motion Blur

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.

Impact of motion cues, color, and luminance on depth perception in optical see-through AR displays

“…A lot of work in AR with relation to speed or motion involves automatic object tracking or trajectory prediction (Chen and Meng, 2010;Gao and Spratling, 2022;Lee et al, 2020;Li et al, 2021;Morzy, 2006). Bedell et al investigated which judgment is perceived first, color change or movement, and found that it depends on motion cycle (Bedell et al, 2003).…”

“…In previous literature, speed and motion cues are considered for object detection and not as factors affecting depth perception (Bedell et al, 2003;Cucchiara et al, 2001;Dubuisson and Jain, 1993;Møller and Hurlbert, 1997). When accounting for speed, these works focus on sequences of frames for automatic object tracking or trajectory prediction (Chen and Meng, 2010;Lee et al, 2020;Li et al, 2021;Morzy, 2006). Self et al found that color and motion-defined shapes activate similar regions in the brain more strongly when used together than either of these cues separately (Self and Zeki, 2004).…”