An Efficient Road Detection Algorithm Based on Parallel Edges

Wenfeng, 王文锋 Wang; Weili, 丁伟利 Ding; Yong, 李勇 Li; Shujun, 杨树军 Yang

doi:10.3788/aos201535.0715001

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the results can be accepted. In this part, the performance of the proposed road detection algorithm is compared to four algorithms proposed by Zhang [10], Yun [22], Kong [4] and Wang [23], respectively. And the results are shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes

Ding

Zhang

et al. 2016

Robotics and Autonomous Systems

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

“…In Fig.14, we compared our experimental results with the algorithm proposed by Wang et. al [23], which has integrated use of parallel edges, road region location information, to achieve the accurate identification of the characteristics of the road. As shown in Fig.14 T is the total number of pixels in the right extracted region.…”

Section: Resultsmentioning

confidence: 99%

Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes

Ding

Zhang

et al. 2016

Robotics and Autonomous Systems

View full text Add to dashboard Cite

“…Essentially, traditional road detection is a problem of region segmentation and labeling in image processing. One of the common methods is to analyze the low-level information of the image, such as color (Duan Zhigang et al 2016;Xiao et al 2016), edge (Wang Wenfeng et al 2015), texture (Zhou et al 2010). Then it obtains segmentation results by segmentation algorithms, such as clustering algorithms.…”

Section: Research On Road Segmentation Algorithmsmentioning

confidence: 99%

A Semi-Supervised Domain Adaptive Learning Approach to Unstructured Road Region Semantic Segmentation for Greenhouse Robots

Gao

Gong

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Efficient drivable region segmentation is a critical for greenhouse robot navigation. State-of-the-art deep learning based road segmentation methods rely largely on labeled datasets to deal with the complexity of unstructured facility agriculture environment. However, the scarcity of annotated datasets limits the model performance. To break the bottleneck, this paper proposes a semi-supervised domain adaptive learning method for unstructured road semantic segmentation. Firstly, we establish a training framework for segmentation models through the transfer learning approach from a synthetic road dataset to an unstructured road dataset. Secondly, we determine the optimal pre-training strategy for solving the greenhouse road segmentation problem. Finally, for the long-tailed distribution of image data in the process of drivable area segmentation, we optimize the loss function to obtain an effective segmentation model for greenhouse robot navigation. For unstructured facility farming scenarios, we created an unstructured road dataset with annotation. Experiments show that, with a small number of labeled data, the road mIoU reaches 98.6%, which is about 10% greater than the existing unstructured road segmentation models to deal with ambiguous boundaries, complex obstacles, and shadow interference. It shows that the proposed method is feasible to leverage the successful existing city self-driving models and datasets to enrich and improve the road segmentation under agricultural scenarios.

show abstract

“…These algorithms are dependent on the effect of image transformation, and they are not always effective for complex illumination environment. The gradient information analysis is mainly used for edge detection [3,[10][11][12][13][14], such as Ref [12] using the watershed algorithm to detect the edge of the road, or fitting the boundary of road by gradient image,. These methods are usually effective for structured roads with sign-lines, but the algorithms are not stable when the road boundary is not obvious or the road surface is cluttered.…”

Section: Introductionmentioning

confidence: 99%