Implementation of a System for Real-Time Detection and Localization of Terrain Objects on Harvested Forest Land

Håkan Lideskog,Songyu Li

doi:10.3390/f12091142

Abstract

Research highlights: An automatic localization system for ground obstacles on harvested forest land based on existing mature hardware and software architecture has been successfully implemented. In the tested area, 98% of objects were successfully detected and could on average be positioned within 0.33 m from their true position in the full range 1–10 m from the camera sensor. Background and objectives: Forestry operations in forest environments are full of challenges; detection and localization of objects in complex forest terrains often require a lot of patience and energy from operators. Successful automatic real-time detection and localization of terrain objects not only can reduce the difficulty for operators but are essential for the automation of harvesting and logging tasks. We intend to implement a system prototype that can automatically locate ground obstacles on harvested forest land based on accessible hardware and common software infrastructure. Materials and Methods: An automatic object detection and localization system based on stereo camera sensing is described and evaluated in this paper. This demonstrated system detects and locates objects of interest automatically utilizing the YOLO (You Only Look Once) object detection algorithm and derivation of object positions in 3D space. System performance is evaluated by comparing the automatic detection results of the tests to manual labeling and positioning results. Results: Results show high reliability of the system for automatic detection and location of stumps and large stones and shows good potential for practical application. Overall, object detection on test tracks was 98% successful, and positional location errors were on average 0.33 m in the full range from 1–10 m from the camera sensor. Conclusions: The results indicate that object detection and localization can be used for better operator assessment of surroundings, as well as input to control machines and equipment for object avoidance or targeting.

Highlights

The difference the results from automatic detection and localFor thebetween target objects that appear in the scene, the successful occurrence of a ization obtained bybounding manual box location information, which was regarded as the true value as detection; overlapping the object by at least 90% is regarded as a successful the benchmark, wehere canwe judge performance of the automatic detection say itthe is aactual
Our results show the feasibility of constructing an automatic object detection and localization system for traditional forestry machines such as forest harvesters and forwarders common to Scandinavian forest environments
We can determine that the error between each automatic localization position and the manual marked position for each object maintain is within a reasonable range

Summary

Introduction

The Nordic region has vast forest cover with abundant forest resources. About three quarters of the total land area in Finland and Sweden are covered by forests and other woodlands. We intend to implement a system prototype that can automatically locate ground obstacles on harvested forest land based on accessible hardware and common software infrastructure. Materials and Methods: An automatic object detection and localization system based on stereo camera sensing is described and evaluated in this paper. This demonstrated system detects and locates objects of interest automatically utilizing the YOLO (You Only Look Once) object detection algorithm and derivation of object positions in 3D space.

Objectives

Methods

Results

Conclusion