Convolutional neural networks on small unmanned aerial systems

In the revolutionary field of deep learning many difficult computer vision challenges of today are being impressively overcome by the application of these cutting edge technologies. The challenge of detecting vehicular objects from aerial imagery is a long-standing interest in computer vision. Performing this accurately in real-time while utilizing the payload bay of a small unmanned aerial system (SUAS) is even more desirable and challenging. In this work, these challenges are successfully surmounted with the use of Faster R-CNN [1], a highly cultivated aerial image dataset, supercomputers, and a dedicated team of SUAS experts. By first training Faster R-CNN on a customized dataset of electro-optical (EO) annotated aerial imagery then empirically testing on supercomputers across hundreds of hyperparameters, the resulting optimized network was successfully integrated into established SUAS operations. This combination of cutting edge technologies lead to strong performance while requiring a fraction of the development time and meeting strict in-flight SWaP requirements.

[1]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[2]  L. Kumar,et al.  Soil Salinity Mapping and Monitoring in Arid and Semi-Arid Regions Using Remote Sensing Technology: A Review , 2013 .

[3]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[4]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[5]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[6]  D. E. Juanico,et al.  Simulated effects of site salinity and inundation on long-term growth trajectory and carbon sequestration in monospecific Rhizophora mucronata plantation in the Philippines , 2014, 1405.6944.

[7]  Daudi S. Simbeye,et al.  Water Quality Monitoring and Control for Aquaculture Based on Wireless Sensor Networks , 2014, J. Networks.

[8]  Philip H. S. Torr,et al.  BING: Binarized normed gradients for objectness estimation at 300fps , 2014, Computational Visual Media.

[9]  Fleurdeliz Maglangit,et al.  Water quality assessment of Bulacao River, Cebu, Philippines using fecal and total coliform as indicators , 2014 .

[10]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[11]  C. Chiang,et al.  A CMOS digitized salinity transducer with calibration circuits for monitoring salinity of ocean environment and aquaculture , 2014, IEEE SENSORS 2014 Proceedings.

[12]  M. Middeljans.  The species composition of the mangrove forest along the Abatan River in Lincod, Maribojoc, Bohol, Philippines and the mangrove forest structure and its regeneration status between managed and unmanaged Nipa palm (Nypa fruticans Wurmb) , 2014 .

[13]  Deepak Khosla,et al.  A neuromorphic system for video object recognition , 2014, Front. Comput. Neurosci..

[14]  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.

[15]  Xiaoou Tang,et al.  A large-scale car dataset for fine-grained categorization and verification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[17]  C. Chiang,et al.  Design of a Calibrated Salinity Sensor Transducer for Monitoring Salinity of Ocean Environment and Aquaculture , 2015, IEEE Sensors Journal.

[18]  A. Blanco,et al.  HYDRODYNAMIC INVESTIGATION OF A SHALLOW TROPICAL LAKE ENVIRONMENT (LAGUNA LAKE, PHILIPPINES) AND ASSOCIATED IMPLICATIONS FOR EUTROPHIC VULNERABILITY , 2014, ASEAN Engineering Journal.

[19]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[20]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[22]  Yu Wang,et al.  Rebooting Computing and Low-Power Image Recognition Challenge , 2015, 2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

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

[24]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[25]  Frédéric Jurie,et al.  Vehicle detection in aerial imagery : A small target detection benchmark , 2016, J. Vis. Commun. Image Represent..

[26]  Aleksey Boyko,et al.  Detecting Cancer Metastases on Gigapixel Pathology Images , 2017, ArXiv.