In this paper, we propose a novel generative framework which uses Generative Adversarial Networks (GANs) to generate features that provide robustness for object detection on reduced-quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. We first evaluate the effect of image quality on both object classification and object bounding box regression. We then test the models resulting from our proposed GAN-DO framework, using two state-of-the-art object detection architectures as the baseline models. We also evaluate the effect of the number of re-trained parameters in the generator of GAN-DO on the accuracy of the final trained model. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher mAP compared to the existing approaches.

This paper presents a novel camera calibration method using a circular calibration pattern. The disadvantages and issues with existing state-of-the-art methods are discussed and are overcome in this work. In the proposed iterative method, the captured images of the circular pattern are undistorted and projected onto a fronto parallel plane. The control points are localized in this fronto parallel plane using a novel approach for more accurately localizing the control points in the images based on adaptive segmentation and ellipse fitting. The localized control points are then projected to their original planes using estimated camera calibration parameters that are refined by minimizing the reprojection error. Simulation results are presented to illustrate the performance of the proposed scheme. These results show that the proposed method reduces the error by up to 57% as compared to the state-of-the-art for high-resolution images, and that the proposed scheme is more robust to blur in the imaged calibration pattern.