Efficient scene understanding for intelligent vehicles using a part-based road representation

Töpfer, Daniel; Spehr, Jens; Effertz, Jan; Stiller, Christoph

doi:10.1109/itsc.2013.6728212

Cited by 12 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing textual explanation methods majorly depend on a separate approach of visual perception, including semantic segmentation, object detection, trajectory analysis, etc. (Xu et al, 2020) (Töpfer et al, 2013) (Wang et al, 2010) However, these approaches pay more attention to high-level contextual elements such as sky, walls, and vegetation (Hoiem et al, 2008). These elements are not vital to the safety of complex road and traffic scenarios (Töpfer et al, 2013).…”

Section: Textual Explanation Methodsmentioning

confidence: 99%

“…(Xu et al, 2020) (Töpfer et al, 2013) (Wang et al, 2010) However, these approaches pay more attention to high-level contextual elements such as sky, walls, and vegetation (Hoiem et al, 2008). These elements are not vital to the safety of complex road and traffic scenarios (Töpfer et al, 2013).…”

Section: Textual Explanation Methodsmentioning

confidence: 99%

“…But many researchers regarded scene explanation as a semantic segmentation problem (Töpfer et al, 2013). Previous studies applied various deep learning networks to assign semantic labels to individual segments and detect the edge and semantic information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation

Zhao¹,

Yun²,

Chai³

et al. 2022

Preprint

View full text Add to dashboard Cite

The complex driving environment brings great challenges to the visual perception of autonomous vehicles.It's essential to extract clear and explainable information from the complex road and traffic scenarios and offer clues to decision and control. However, the previous scene explanation had been implemented as a separate model. The black box model makes it difficult to interpret the driving environment. It cannot detect comprehensive textual information and requires a high computational load and time consumption.Thus, this study proposed a comprehensive and efficient textual explanation model. From 336k video frames of the driving environment, critical images of complex road and traffic scenarios were selected into a dataset.Through transfer learning, this study established an accurate and efficient segmentation model to obtain the critical traffic elements in the environment. Based on the XGBoost algorithm, a comprehensive model was developed. The model provided textual information about states of traffic elements, the motion of conflict objects, and scenario complexity. The approach was verified on the real-world road. It improved the perception accuracy of critical traffic elements to 78.8%. The time consumption reached 13 minutes for each epoch, which was 11.5 times more efficient than the pre-trained network. The textual information analyzed from the model was also accordant with reality. The findings offer clear and explainable information about the complex driving environment, which lays a foundation for subsequent decision and control. It can improve the visual perception ability and enrich the prior knowledge and judgments of complex traffic situations.

show abstract

Section: Textual Explanation Methodsmentioning

confidence: 99%

Section: Textual Explanation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation

Zhao¹,

Yun²,

Chai³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Consequently, an occupancy grid is created in [11]. As an alternative, the authors of [12] propose to divide detected lane structures into patches and to connect them as an undirected graphical model. Geometrically extrapolating the road out of the sensor range allows to infer information at occlusions.…”

Section: A Related Workmentioning

confidence: 99%

Intersection Warning System for Occlusion Risks Using Relational Local Dynamic Maps

Damerow

Puphal

Flade

et al. 2018

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

This work addresses the task of risk evaluation in traffic scenarios with limited observability due to restricted sensorial coverage. Here, we concentrate on intersection scenarios that are difficult to access visually. To identify the area of sight, we employ ray casting on a local dynamic map providing geometrical information and road infrastructure. Based on the area with reduced visibility, we first model scene entities that pose a potential risk without being visually perceivable yet. Then, we predict a worst-case trajectory in the survival analysis for collision risk estimation. Resulting risk indicators are utilized to evaluate the driver's current behavior, to warn the driver in critical situations, to give suggestions on how to act safely or to plan safe trajectories. We validate our approach by applying the resulting intersection warning system on real world scenarios. The proposed system's behavior reveals to mimic the general behavior of a correctly acting human driver.

show abstract

“…Part-based object representations are of key importance for many computer vision tasks such as object recognition [108,9,77,1], pose estimation [32,101,14,104], action detection [93], and scene understanding [70,81,75]. Currently, part-based approaches often represent objects as a set of sparse keypoints, because these are easy to annotate in large-scale datasets for training deep neural networks.…”

Section: Introductionmentioning

confidence: 99%

Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles

Liu¹,

Kortylewski²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Part segmentations provide a rich and detailed partlevel description of objects, but their annotation requires an enormous amount of work. In this paper, we introduce CGPart, a comprehensive part segmentation dataset that provides detailed annotations on 3D CAD models, synthetic images, and real test images. CGPart includes 21 3D CAD models covering 5 vehicle categories, each with detailed per-mesh part labeling. The average number of parts per category is 24, which is larger than any existing datasets for part segmentation on vehicle objects. By varying the rendering parameters, we make 168, 000 synthetic images from these CAD models, each with automatically generated part segmentation ground-truth. We also annotate part segmentations on 200 real images for evaluation purposes. To illustrate the value of CGPart, we apply it to image part segmentation through unsupervised domain adaptation (UDA). We evaluate several baseline methods by adapting top-performing UDA algorithms from related tasks to part segmentation. Moreover, we introduce a new method called Geometric-Matching Guided domain adaptation (GMG), which leverages the spatial object structure to guide the knowledge transfer from the synthetic to the real images. Experimental results demonstrate the advantage of our new algorithm and reveal insights for future improvement. We will release our data and code.

show abstract

Efficient scene understanding for intelligent vehicles using a part-based road representation

Cited by 12 publications

References 20 publications

Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation

Efficient textual explanations for complex road and traffic scenarios based on semantic segmentation

Intersection Warning System for Occlusion Risks Using Relational Local Dynamic Maps

Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles

Contact Info

Product

Resources

About