DeepAI AI Chat
Log In Sign Up

Detector With Focus: Normalizing Gradient In Image Pyramid

by   Yonghyun Kim, et al.

An image pyramid can extend many object detection algorithms to solve detection on multiple scales. However, interpolation during the resampling process of an image pyramid causes gradient variation, which is the difference of the gradients between the original image and the scaled images. Our key insight is that the increased variance of gradients makes the classifiers have difficulty in correctly assigning categories. We prove the existence of the gradient variation by formulating the ratio of gradient expectations between an original image and scaled images, then propose a simple and novel gradient normalization method to eliminate the effect of this variation. The proposed normalization method reduce the variance in an image pyramid and allow the classifier to focus on a smaller coverage. We show the improvement in three different visual recognition problems: pedestrian detection, pose estimation, and object detection. The method is generally applicable to many vision algorithms based on an image pyramid with gradients.


page 1

page 2

page 3

page 4


Consistent Scale Normalization for Object Recognition

Scale variation remains a challenge problem for object detection. Common...

Template Matching based Object Detection Using HOG Feature Pyramid

This article provides a step by step development of designing a Object D...

An Analysis of Scale Invariance in Object Detection - SNIP

An analysis of different techniques for recognizing and detecting object...

Scale Normalized Image Pyramids with AutoFocus for Object Detection

We present an efficient foveal framework to perform object detection. A ...

Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention

CNNs, initially inspired by human vision, differ in a key way: they samp...

Cursive Scene Text Analysis by Deep Convolutional Linear Pyramids

The camera captured images have various aspects to investigate. Generall...

Code Repositories