Efficient Object Detection for High Resolution Images

TL;DR

This paper introduces efficient methods for object detection in high-resolution images by combining feature-based bounding box prediction and adaptive region search, improving speed and accuracy in detecting small objects.

Contribution

The paper proposes a novel approach that combines adjacent visual feature prediction with high-level feature-guided search for better high-resolution object detection.

Findings

Effective detection of small objects in high-resolution images

Improved computational efficiency over existing methods

Demonstrated success on SUN 2012 dataset

Abstract

Efficient generation of high-quality object proposals is an essential step in state-of-the-art object detection systems based on deep convolutional neural networks (DCNN) features. Current object proposal algorithms are computationally inefficient in processing high resolution images containing small objects, which makes them the bottleneck in object detection systems. In this paper we present effective methods to detect objects for high resolution images. We combine two complementary strategies. The first approach is to predict bounding boxes based on adjacent visual features. The second approach uses high level image features to guide a two-step search process that adaptively focuses on regions that are likely to contain small objects. We extract features required for the two strategies by utilizing a pre-trained DCNN model known as AlexNet. We demonstrate the effectiveness of our algorithm by showing its performance on a high-resolution image subset of the SUN 2012 object detection dataset.