Efficient Face Detection in the Fisheye Image Domain

Significant progress has been made for face detection from normal images in recent years; however, accurate and fast face detection from fisheye images remains a challenging issue because of serious fisheye distortion in the peripheral region of the image. To improve face detection accuracy, we propose a light-weight location-aware network to distinguish the peripheral region from the central region in the feature learning stage. To match the face detector, the shape and scale of the anchor (bounding box) is made location dependent. The overall face detection system performs directly in the fisheye image domain without rectification and calibration and hence is agnostic of the fisheye projection parameters. Experiments on Wider-360 and real-world fisheye images using a single CPU core indeed show that our method is superior to the state-of-the-art real-time face detector RFB Net.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Shifeng Zhang,et al.  Faceboxes: A CPU real-time and accurate unconstrained face detector , 2019, Neurocomputing.

[3]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[4]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[5]  Dongyoon Han,et al.  EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse , 2019, ArXiv.

[6]  Stefanos Zafeiriou,et al.  A survey on face detection in the wild: Past, present and future , 2015, Comput. Vis. Image Underst..

[7]  Homer H Chen,et al.  Deep Face Rectification for 360° Dual-Fisheye Cameras , 2020, IEEE Transactions on Image Processing.

[8]  Shifeng Zhang,et al.  RefineFace: Refinement Neural Network for High Performance Face Detection , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Chunyu Lin,et al.  Unsupervised fisheye image correction through bidirectional loss with geometric prior , 2020, J. Vis. Commun. Image Represent..

[10]  Stan Z. Li,et al.  FLDet: A CPU Real-time Joint Face and Landmark Detector , 2019, 2019 International Conference on Biometrics (ICB).

[11]  Xu Tang,et al.  PyramidBox: A Context-assisted Single Shot Face Detector , 2018, ECCV.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yunhong Wang,et al.  Receptive Field Block Net for Accurate and Fast Object Detection , 2017, ECCV.

[14]  Weiming Shen,et al.  Learning to Calibrate Straight Lines for Fisheye Image Rectification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Dumitru Erhan,et al.  Scalable Object Detection Using Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Yi Zhang,et al.  Line-based Multi-Label Energy Optimization for fisheye image rectification and calibration , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Jiwen Lu,et al.  Learning Reasoning-Decision Networks for Robust Face Alignment , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[20]  Jian Yang,et al.  DSFD: Dual Shot Face Detector , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Yu-Chiang Frank Wang,et al.  Self-Supervised Deep Learning for Fisheye Image Rectification , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[23]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Stan Z. Li,et al.  Single-Shot Scale-Aware Network for Real-Time Face Detection , 2019, International Journal of Computer Vision.

[25]  Jiwen Lu,et al.  Context-Aware Local Binary Feature Learning for Face Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Li-Jia Li,et al.  Multi-view Face Detection Using Deep Convolutional Neural Networks , 2015, ICMR.

[27]  Peiyun Hu,et al.  Finding Tiny Faces , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Yohan Dupuis,et al.  Robust Radial Face Detection for Omnidirectional Vision , 2013, IEEE Transactions on Image Processing.

[29]  Lixin Fan,et al.  Object Detection in Equirectangular Panorama , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[30]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[31]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[32]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Ivan V. Bajic,et al.  Datasets for face and object detection in fisheye images , 2019, Data in brief.

[34]  Kuk-Jin Yoon,et al.  SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360° Images , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Shuo Yang,et al.  WIDER FACE: A Face Detection Benchmark , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Chenhao Wang,et al.  TinaFace: Strong but Simple Baseline for Face Detection , 2020, ArXiv.

[38]  Rodney G. Vaughan,et al.  FDDB-360: Face Detection in 360-Degree Fisheye Images , 2019, 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[39]  Jun Yu,et al.  FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification , 2018, ECCV.