SR-POD : sample rotation based on principal-axis orientation distribution for data augmentation in deep object detection
Xi, Yue and Zheng, Jiangbin and Li, Xiuxiu and Xu, Xinying and Ren, Jinchang and Xie, Gang (2018) SR-POD : sample rotation based on principal-axis orientation distribution for data augmentation in deep object detection. Cognitive Systems Research, 52. pp. 144-154. (https://doi.org/10.1016/j.cogsys.2018.06.014)
Preview |
Text.
Filename: Xi_etal_CSR2018_SR_POD_sample_rotation_based_on_principal_axis_orientation.pdf
Accepted Author Manuscript License: Download (1MB)| Preview |
Abstract
Convolutional neural networks (CNNs) have outperformed most state-of-the-art methods in object detection. However, CNNs suffer the difficulty of detecting objects with rotation, because the dataset used to train the CCNs often does not contain sufficient samples with various angles of orientation. In this paper, we propose a novel data-augmentation approach to handle samples with rotation, which utilizes the distribution of the object's orientation without the time-consuming process of rotating the sample images. Firstly, we present an orientation descriptor, named as "principal-axis orientation" to describe the orientation of the object's principal axis in an image and estimate the distribution of objects’ principal-axis orientations (PODs) of the whole dataset. Secondly, we define a similarity metric to calculate the POD similarity between the training set and an additional dataset, which is built by randomly selecting images from the benchmark ImageNet ILSVRC2012 dataset. Finally, we optimize a cost function to obtain an optimal rotation angle, which indicates the highest POD similarity between the two aforementioned data sets. In order to evaluate our data augmentation method for object detection, experiments, conducted on the benchmark PASCAL VOC2007 dataset, show that with the training set augmented using our method, the average precision (AP) of the Faster RCNN in the TV-monitor is improved by 7.5%. In addition, our experimental results also demonstrate that new samples generated by random rotation are more likely to result in poor performance of object detection.
ORCID iDs
Xi, Yue, Zheng, Jiangbin, Li, Xiuxiu, Xu, Xinying, Ren, Jinchang ORCID: https://orcid.org/0000-0001-6116-3194 and Xie, Gang;-
-
Item type: Article ID code: 65272 Dates: DateEvent31 December 2018Published4 July 2018Published Online25 June 2018AcceptedSubjects: Medicine > Internal medicine > Neuroscience. Biological psychiatry. Neuropsychiatry Department: Technology and Innovation Centre > Sensors and Asset Management
Faculty of Engineering > Electronic and Electrical EngineeringDepositing user: Pure Administrator Date deposited: 27 Aug 2018 12:03 Last modified: 03 Oct 2024 00:28 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/65272