Fast ROI Detection for Speed up in a CNN based Object Detection

DETECTION In order to enhance the operation speed of a CNN based object detection method, this paper proposes a method for detecting ROI. When a CNN only processes ROI instead of Abstract Fast operation of a CNN based object detection is important in many application areas. It is an efficient approach to reduce the size of an input image. However, it is difficult to find an area that includes a target object with minimal computation. This paper proposes a ROI detection method that is fast and robust to noise. The proposed method is not affected by a flicker line noise that is a kind of aliasing between camera and LED light. Fast operation is achieved by using down-sampling efficiently. The accuracy of the proposed ROI detection method is 92.5% and the operation time for a frame with a resolution of 640 x 360 is 0.388msec.

Paper

Full text

PDF

Fast ROI Detection for Speed up in a CNN based Object Detection

Semantic Scholar · Computer Science · 2019

Abstract

DETECTION In order to enhance the operation speed of a CNN based object detection method, this paper proposes a method for detecting ROI. When a CNN only processes ROI instead of Abstract Fast operation of a CNN based object detection is important in many application areas. It is an efficient approach to reduce the size of an input image. However, it is difficult to find an area that includes a target object with minimal computation. This paper proposes a ROI detection method that is fast and robust to noise. The proposed method is not affected by a flicker line noise that is a kind of aliasing between camera and LED light. Fast operation is achieved by using down-sampling efficiently. The accuracy of the proposed ROI detection method is 92.5% and the operation time for a frame with a resolution of 640 x 360 is 0.388msec.

Similar papers

© 2026 NYSGPT2525 LLC