O'Reilly logo

Java Deep Learning Projects by Md. Rezaul Karim

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Object detection from videos

Let's think of a simple scenario before digging down deeper. Suppose we have a video clip containing the movement of a cat or wolf in a forest. Now we want to detect this animal but while on the move at each timestep.

The following graph shows the challenges in such a scenario. The red boxes are ground truth annotations. The upper part of the figure (that is a) shows still-image object detection methods have large temporal fluctuations across frames, even on ground truth bounding boxes. The fluctuations may result from motion blur, video defocus, part occlusion and bad pose. Information from boxes of the same object on adjacent frames needs to be utilized for object detection in video.

On the other hand, (b) shows ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required