학술논문

Scale optimization for full-image-CNN vehicle detection
Document Type
Conference
Source
2017 IEEE Intelligent Vehicles Symposium (IV) Intelligent Vehicles Symposium (IV), 2017 IEEE. :785-791 Jun, 2017
Subject
Communication, Networking and Broadcast Technologies
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Proposals
Benchmark testing
Feature extraction
Object detection
Detectors
Convolution
Neural networks
Language
Abstract
Many state-of-the-art general object detection methods make use of shared full-image convolutional features (as in Faster R-CNN). This achieves a reasonable test-phase computation time while enjoys the discriminative power provided by large Convolutional Neural Network (CNN) models. Such designs excel on benchmarks 1 which contain natural images but which have very unnatural distributions, i.e. they have an unnaturally high-frequency of the target classes and a bias towards a “friendly” or “dominant” object scale. In this paper we present further study of the use and adaptation of the Faster R-CNN object detection method for datasets presenting natural scale distribution and unbiased real-world object frequency. In particular, we show that better alignment of the detector scale sensitivity to the extant distribution improves vehicle detection performance. We do this by modifying both the selection of Region Proposals, and through using more scale-appropriate full-image convolution features within the CNN model. By selecting better scales in the region proposal input and by combining feature maps through careful design of the convolutional neural network, we improve performance on smaller objects. We significantly increase detection AP for the KITTI dataset car class from 76.3% on our baseline Faster R-CNN detector to 83.6% in our improved detector.