Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression

Feng, Xue; Ming, Anlong; Zhou, Yu

doi:10.1109/tip.2020.3026636

Cited by 14 publications

(3 citation statements)

References 39 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirdly, based on the evidence given by the two subnetworks, an uncertainty-aware fusion (UAF) module is designed to perceive the uncertainty of each modality, and determine the probability and uncertainty that a pixel belongs to road or non-road. In practical application, the perceived uncertainty can be provided to the self-driving system for further obstacle discovery [15], [16]. As shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

Fast Road Segmentation via Uncertainty-aware Symmetric Network

Chang¹,

Xue²,

Sheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The high performance of RGB-D based road segmentation methods contrasts with their rare application in commercial autonomous driving, which is owing to two reasons: 1) the prior methods cannot achieve high inference speed and high accuracy in both ways; 2) the different properties of RGB and depth data are not well-exploited, limiting the reliability of predicted road. In this paper, based on the evidence theory, an uncertainty-aware symmetric network (USNet) is proposed to achieve a trade-off between speed and accuracy by fully fusing RGB and depth data. Firstly, cross-modal feature fusion operations, which are indispensable in the prior RGB-D based methods, are abandoned. We instead separately adopt two light-weight subnetworks to learn road representations from RGB and depth inputs. The light-weight structure guarantees the real-time inference of our method. Moreover, a multiscale evidence collection (MEC) module is designed to collect evidence in multiple scales for each modality, which provides sufficient evidence for pixel class determination. Finally, in uncertainty-aware fusion (UAF) module, the uncertainty of each modality is perceived to guide the fusion of the two subnetworks. Experimental results demonstrate that our method achieves a state-of-the-art accuracy with real-time inference speed of 43+ FPS. The source code is available at https: //github.com/morancyc/USNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast Road Segmentation via Uncertainty-aware Symmetric Network

Chang¹,

Xue²,

Sheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…N OWADAYS, the visual text exists widely in the scenarios of our daily life. Since most videos contain text, detecting and tracking visual text from a video is a significant step in many application, such as video content review [1], [2], road signs understanding [3], [4], video retrieval [5], [6], automatic drive [7], [8], [9], [10], [11], [12], [13], etc.…”

Section: Introductionmentioning

confidence: 99%

Video Text Tracking With a Spatio-Temporal Complementary Model

Gao,

Li,

Zhang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Text tracking is to track multiple texts in a video, and construct a trajectory for each text. Existing methods tackle this task by utilizing the tracking-by-detection framework, i.e., detecting the text instances in each frame and associating the corresponding text instances in consecutive frames. We argue that the tracking accuracy of this paradigm is severely limited in more complex scenarios, e.g., owing to motion blur, etc., the missed detection of text instances causes the break of the text trajectory. In addition, different text instances with similar appearance are easily confused, leading to the incorrect association of the text instances. To this end, a novel spatio-temporal complementary text tracking model is proposed in this paper. We leverage a Siamese Complementary Module to fully exploit the continuity characteristic of the text instances in the temporal dimension, which effectively alleviates the missed detection of the text instances, and hence ensures the completeness of each text trajectory. We further integrate the semantic cues and the visual cues of the text instance into a unified representation via a text similarity learning network, which supplies a high discriminative power in the presence of text instances with similar appearance, and thus avoids the misassociation between them. Our method achieves state-of-the-art performance on several public benchmarks. The source code is available at https://github.com/lsabrinax/VideoTextSCM.

show abstract

“…The near clusters are classified by forest F(1) , and the clusters at a middle distance are classified by forest F(1) and F(2) . Analogically, the far clusters correspond to forest F(1) , F(2) , and F(3) . The red dotted box shows the combination rule of the operator ⊕.…”

mentioning

confidence: 98%