Feature-based visual tracking for agricultural implements

Abstract: Systems which utilize implement-mounted cameras for machinery feedback, such as row crop cultivators and sectional sprayers, can be upgraded to provide high-accuracy ground speed and tracking data using visual tracking algorithms. Vector data produced by visual tracking can be incorporated into control systems to compensate for implement dynamics in complement with RTK-GNSS receivers and other sensors. Variations of the SURF, SIFT, and ORB feature-descriptor algorithms were evaluated using a dataset of 640×480 pixel videos on six surfaces (gravel, asphalt, grass, seedlings, residue, and pasture) for speeds from 1 to 5 m/s. Feature-descriptor matching of consecutive video frames was tested using two methods of the k-Nearest Neighbors (kNN) algorithm: (1) 1NN with cross-checking, and (2) 2NN with the ratio-test. Ground speed and tracking direction were calculated using a fast histogram filter to reject outliers between frames. Compared to RTK-GNSS, ORB with CLAHE pre-processing (CLORB) and 1NN cross-checking was found to be the most robust with respect to real-time applications. For 95% of measurements, CLORB achieved an error of 0.23 m/s. Similar accuracy was achieved with SURF, U-SURF, and SIFT, but CLORB was capable of producing vector data in real-time (approximately 25 Hz), whereas SURF, U-SURF, and SIFT were only capable of 15 Hz or less.

[1]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[2]  Tobias Höllerer,et al.  Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking , 2011, International Journal of Computer Vision.

[3]  Saurabh Maheshwari,et al.  Contrast limited adaptive histogram equalization based enhancement for real time video system , 2014, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[4]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[5]  N. D. Tillett,et al.  Automated Crop and Weed Monitoring in Widely Spaced Cereals , 2006, Precision Agriculture.

[6]  James R. Bergen,et al.  Visual odometry for ground vehicle applications , 2006, J. Field Robotics.

[7]  Robert S. Freeland,et al.  Comparison of Tractor Ground Speed Measurement Techniques , 1985 .

[8]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[9]  A. Escolà,et al.  Variable rate application of plant protection products in vineyard using ultrasonic sensors , 2007 .

[10]  J. S. Townsend,et al.  A New Slip Monitor for Traction Equipment , 1977 .

[11]  S. Gan-Mor,et al.  Implement lateral position accuracy under RTK-GPS tractor guidance , 2007 .

[12]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[14]  Keith E. Muller,et al.  Contrast-limited adaptive histogram equalization: speed and effectiveness , 1990, [1990] Proceedings of the First Conference on Visualization in Biomedical Computing.

[15]  Eli Shechtman,et al.  In defense of Nearest-Neighbor based image classification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.