Efficient Object Detection for High Resolution Images
This work addresses a domain-specific problem for computer vision researchers and practitioners dealing with high-resolution image analysis, but it is incremental as it builds on existing DCNN methods.
The paper tackles the problem of inefficient object proposal generation for high-resolution images with small objects, a bottleneck in object detection systems, by combining two strategies—predicting bounding boxes from adjacent features and using high-level features to guide a search—and demonstrates effectiveness on a high-resolution subset of the SUN 2012 dataset.
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.