Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks
Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks
复制标题
DOI：
10.1109/ijcnn.2019.8851859
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Ranjith Dinakaran;Philip Easom;Li Zhang;A. Bouridane;Richard M. Jiang;E. Edirisinghe
中科院分区：
文献类型：
--
作者：
Ranjith Dinakaran;Philip Easom;Li Zhang;A. Bouridane;Richard M. Jiang;E. Edirisinghe
在这项工作中，我们研究了将具有单镜头检测器（SSD）的深度卷积生成对抗网络（DCGAN）作为数据处理技术来应对野外行人检测挑战的可行性。具体来说，我们尝试使用填充完成来生成丢失像素的图像的随机变换，以扩展现有的标记数据集。在我们的工作中，GAN在低分辨率图像上进行了密集训练，以消除野外行人检测的挑战，并考虑了人类，以及智能城市中很少有其他类别的检测。通过训练GAN模型沿着SSD执行的对象检测器实验提供了结果的实质性改进。这种方法在GAN网络用于对象检测的当前技术水平中提供了一个非常有趣的概述。利用加拿大高等研究院（CIFAR）、加州理工学院（Caltech）、KITTI数据集对网络进行了不同分辨率下的训练和测试，并给出了DCGAN与SSD级联和SSD本身级联的实验结果。
In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion to generate random transformations of images with missing pixels to expand existing labelled datasets. In our work, GAN’s been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showed between DCGAN cascaded with SSD and SSD itself.