Novel machine vision methods for outdoor and built environments

Sluzek, Andrzej

doi:10.1016/j.autcon.2009.12.002

Cited by 4 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, little attention has been given to the problem of locating optical markers (not just for camera calibration) in outdoor settings, where lighting may vary not only in intensity but also color and global histogram distribution. Principles of machine vision techniques have been proposed by [21], who claims that accuracy of object detection is enhanced when optical markers are used; however, no implementation is provided.…”

Section: Related Workmentioning

confidence: 99%

A robust methodology for outdoor optical mark recognition

Andrade

Trabasso

Eguti

et al. 2017

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Outdoor optical mark recognition is an extremely useful tool for recognition of large industrial equipment and application of computer vision-based systems for tracking and positioning. However, current algorithms rely on thresholding and corner detection to identify checkerboard-like patterns, which is not appropriate for non-uniform lighting conditions. This paper presents a robust methodology to identify optical markers in outdoor environments. A GPU-based region filling algorithm automatically detects all contiguous color regions without computing seed points. Post-processing steps extract highlevel information from these regions. Analysis of identified contiguous color region allows simultaneous identification of all checkerboard and targets (concentric regions) in the scene. Analysis of variance demonstrates that the proposed methodology is robust to lighting, environment, perspective, and occlusion. Tests indicate that precision and recall for checkerboard and target identification in outdoor conditions are expected to be above 97%. The parallel algorithm implementation using OpenCL yields better results and is two times faster than previous region filling algorithms, taking about 0.6 s to process a full-HD picture using modern hardware Keywords Computer vision Á Optical mark recognition Á OpenCL Á Parallel processing Á Design of experiments Á Heterogeneous computing

show abstract

Section: Related Workmentioning

confidence: 99%

A robust methodology for outdoor optical mark recognition

Andrade

Trabasso

Eguti

et al. 2017

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…The specific robotic system modules used (sensors, illumination, and manipulator design, including degrees of freedom, dimensions, and controls) also affect the image quality and thus influence detection performance. Therefore, segmentation algorithms developed for other domains (e.g., medical imaging [15,16], or sensing for navigation in indoor environments [17,18]) often fail in outdoor and agricultural domains [2,19,20,21]. To overcome such variable conditions, some parameters of the environment must be stabilized.…”

Section: Introductionmentioning

confidence: 99%

Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting

Arad

Kurtser

Barnea

et al. 2019

Sensors

View full text Add to dashboard Cite

Current harvesting robots are limited by low detection rates due to the unstructured and dynamic nature of both the objects and the environment. State-of-the-art algorithms include color- and texture-based detection, which are highly sensitive to the illumination conditions. Deep learning algorithms promise robustness at the cost of significant computational resources and the requirement for intensive databases. In this paper we present a Flash-No-Flash (FNF) controlled illumination acquisition protocol that frees the system from most ambient illumination effects and facilitates robust target detection while using only modest computational resources and no supervised training. The approach relies on the simultaneous acquisition of two images—with/without strong artificial lighting (“Flash”/“no-Flash”). The difference between these images represents the appearance of the target scene as if only the artificial light was present, allowing a tight control over ambient light for color-based detection. A performance evaluation database was acquired in greenhouse conditions using an eye-in-hand RGB camera mounted on a robotic manipulator. The database includes 156 scenes with 468 images containing a total of 344 yellow sweet peppers. Performance of both color blob and deep-learning detection algorithms are compared on Flash-only and FNF images. The collected database is made public.

show abstract

“…In the paper by Śluzek [40], the principles of two methods that can significantly improve the performance of the vision system under difficult conditions were discussed. The first method (based on gated imaging) is a specialized image acquisition technique, while the second method addresses an important problem of object detection in complex environments.…”

mentioning

confidence: 99%

Automation and robotics in construction: International research and achievements

Zavadskas

2010

Automation in Construction

View full text Add to dashboard Cite

Novel machine vision methods for outdoor and built environments

Cited by 4 publications

References 33 publications

A robust methodology for outdoor optical mark recognition

A robust methodology for outdoor optical mark recognition

Controlled Lighting and Illumination-Independent Target Detection for Real-Time Cost-Efficient Applications. The Case Study of Sweet Pepper Robotic Harvesting

Automation and robotics in construction: International research and achievements

Contact Info

Product

Resources

About