Application of the LIDAR technology for obstacle detection during the operation of agricultural vehicles.

Doerr, Z., Mohsenimanesh, A., Laguë, C., and McLaughlin, N.B. (2013). "Application of the LIDAR technology for obstacle detection during the operation of agricultural vehicles.", Canadian Biosystems Engineering, 55, pp. 2.9-2.16. doi : 10.7451/CBE.2013.55.2.9  Access to full text


Many algorithms have been proposed in the literature for the detection of foreign objects or obstacles to the operation of autonomous vehicles. However, a comparative evaluation of these existing approaches is still lacking. In this study, multiple feature recognition algorithms (average height, density, connectivity, and discontinuity methods) were evaluated for the identification of three types of foreign objects placed in four types of crops (range of crop height: 20 – 80 cm) under different field and operating conditions. The field experiments were completed using a SICK laser measurement system (LMS) 291-S14 scanner that was placed on a tractor to scan standing crops in which the standard test objects had been placed. The data collected by the sensor was analyzed using the software MATLAB 2D and 3D versions. The average height method allowed for a 72.4% average object detection rate while the connectivity method only resulted in a successful object detection rate of 18% for all the experiments. It was also found that the crop density or foliage cover had a negative impact on the detection rate for shorter test objects with the higher rates of obstacle detection being achieved for objects significantly taller than crops. Increasing vehicle speed was also found to reduce detection abilities due to lower scan resolution per distance travelled.

Date modified: