Aerial detection part3
- 1. Aerial Object Detection HyeongJun Kwon 2019-2
- 2. Contents 2 1. EAST: An Efficient and Accurate Scene Text Detector 2. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
- 3. EAST: An Efficient and Accurate Scene Text Detector 3 Network Overview Pipeline Input image Multi-channel FCN Multi-channel FCN Multi-oriented Task-wise boxes
- 4. 4 EAST: An Efficient and Accurate Scene Text Detector Main Contributions : 1. propose two stage(step) method : FCN and NMS merging stage 2. pipeline is flexible
- 5. 5 EAST: An Efficient and Accurate Scene Text Detector Relate work: PVANet
- 6. 6 EAST: An Efficient and Accurate Scene Text Detector Pipeline input conv2 conv3 conv1 conv3 merging1 merging2 merging3 For reduce computation cost, using U-shape not using HyperNet in PVANet that merge all feature maps output
- 7. EAST: An Efficient and Accurate Scene Text Detector 7 Label Generation
- 8. EAST: An Efficient and Accurate Scene Text Detector 8 Label Generation: Score Map Generation Score map generation eq 𝑟𝑖 = min(D 𝑝𝑖, 𝑝 𝑖 𝑚𝑜𝑑 4 +1 , D 𝑝𝑖, 𝑝 𝑖+2 𝑚𝑜𝑑 4 +1 we shrink it by moving its two endpoints inward along the edge by 0.3𝑟𝑖 and 0.3𝑟 𝑖 𝑚𝑜𝑑 4 +1 espectively.
- 9. 9 EAST: An Efficient and Accurate Scene Text Detector 𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔 Label Generation: Loss Where Y = 𝐹S is the prediction of the score map, and Y∗ is the ground truth 𝐿 𝑠 : loss for score map 𝐿 𝑔 : loss for geometry
- 10. 10 EAST: An Efficient and Accurate Scene Text Detector 𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔 Label Generation: Loss RBOX: 𝐿 𝑔 = 𝐿 𝐴𝐴𝐵𝐵 + 𝜆 𝜃 𝐿 𝜃 𝐿 𝑠 : loss for score map 𝐿 𝑔 : loss for geometry 𝐿 𝑔 = 𝐿QUAD Q, Q∗ = min Q∈𝑃 𝑄∗ 𝑐 𝑖∈CQ 𝑐 𝑖∈CQ smoothed 𝐿1 𝑐𝑖 − 𝑐𝑖 8 × 𝑁 𝑄∗ QUAD:
- 11. 11 EAST: An Efficient and Accurate Scene Text Detector Locality-Aware NMS Problem: A naïve NMS algorithm runs in 𝑂 𝑛2 where 𝑛 is the number of candidate geometries. The geometries from nearby pixels tend to be highly correlated. Solution: locality-aware NMS 𝑎 = WEIGHTEDMERGE 𝑔, 𝑝 , then 𝑎i = V 𝑔 𝑔𝑖 + 𝑉 𝑝 𝑝𝑖 and V 𝑎 = V 𝑔 + V(𝑝)
- 12. 12 EAST: An Efficient and Accurate Scene Text Detector
- 13. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 13 Network Overview
- 14. 14 Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery Main Contributions : 1. new joint image cascade and feature pyramid network(ICN and FPN) 2. design a DIN module as a domain adaptation module 3. new loss function to shape rectangles by constraining the angles between the edges to 90 degrees
- 15. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 15 ICN, FPN and Deformable Inception Subnetworks • Appropriate weights sharing • Resize image size by bilinear interpolation ICN • The low-level semantic feature from high resolution • The high-level semantic feature from low-level resolution
- 16. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 16 ICN, FPN and Deformable Inception Subnetworks
- 17. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 17 R-RPN Characteristics: 1. no difference between the front and back of objects 2. initialize anchor by using dimension clustering in YOLO v2 3. use the smooth 𝑙1 loss to regress the four coordinates
- 18. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 18 R-ROI Characteristics: 1. penalize angles that are not 90 degree 2. initialize anchor by using dimension clustering in YOLO v2 3. use the smooth 𝑙1 loss to regress the four coordinates penalize angles that are not 90 degree
- 19. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 19 Objective
- 20. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 20 Objective
- 21. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 21 Result
- 22. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 22 Result
- 23. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 23 Result
- 24. Reference 24 EAST: PVANET: Deep but lightweight neural networks for real-time object detection. Balanced-cross entropy: Holistically-nested edge detection Scene text detection via holistic, multi-channel prediction. U-shape: U-net: Convolu-tional networks for biomedical image segmentation. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery: Soft-NMS: Improving object detection with one line of code. IoU distance: Yolo9000: Better, faster, stronger. DIN: deformable convolutional networks
Editor's Notes
- #17: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #18: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #19: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #20: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #21: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #22: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #23: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #24: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
- #25: DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.