DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block

Jiang, Wei; Wu, Yan; Guan, Linting; Zhao, Junqiao

doi:10.1109/icra.2019.8794476

Cited by 27 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few years, various vision-based parking slot detection methods in the around view image have emerged. These approaches mainly could be subdivided into three categories: line-based methods [8,9,27,28], marking point-based methods [10,11,[19][20][21][22], and segmentation-based methods [24,25,29]. Hamada et al [27] used the Sobel filter and probabilistic Hough transform to obtain lines as the potential parking slot markers.…”

Section: Vision-based Parking Slot Detection In the Around View Imagementioning

confidence: 99%

“…The VH-stage was specially designed to extract linear features, containing independent horizontal and vertical convolution kernels. Subsequently, Jiang et al [25] proposed a DFNet network, which added dynamic loss weights and residual fusion block to improve the accuracy of line segmentation. However, these semantic segmentation methods need post-processing to obtain the parking slot, which is time-consuming and inaccurate.…”

Section: Vision-based Parking Slot Detection In the Around View Imagementioning

confidence: 99%

“…However, this method is based on the Faster R-CNN baseline and it cannot meet the real-time requirements. Moreover, a few semantic segmentation-based methods were proposed in recent years, such as VH-HFCN [24] and DFNet [25]. Despite these methods having outstanding performance in ground markings segmentation, they need post-processing to generate parking slots, which is time-consuming and inaccurate.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Vacant Parking Slot Detection in the Around View Image Based on Deep Learning

Cao

Yan

et al. 2020

Sensors

View full text Add to dashboard Cite

Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parking slot detection method based on deep learning, namely VPS-Net. VPS-Net converts the vacant parking slot detection into a two-step problem, including parking slot detection and occupancy classification. In the parking slot detection stage, we propose a parking slot detection method based on YOLOv3, which combines the classification of the parking slot with the localization of marking points so that various parking slots can be directly inferred using geometric cues. In the occupancy classification stage, we design a customized network whose size of convolution kernel and number of layers are adjusted according to the characteristics of the parking slot. Experiments show that VPS-Net can detect various vacant parking slots with a precision rate of 99.63% and a recall rate of 99.31% in the ps2.0 dataset, and has a satisfying generalizability in the PSV dataset. By introducing a multi-object detection network and a classification network, VPS-Net can detect various vacant parking slots robustly.

show abstract

Section: Vision-based Parking Slot Detection In the Around View Imagementioning

confidence: 99%

Section: Vision-based Parking Slot Detection In the Around View Imagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vacant Parking Slot Detection in the Around View Image Based on Deep Learning

Cao

Yan

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…To realize larger Field of View (FoV) of semantic perception, research efforts have been made on fisheye image segmentation [16], panoramic semantic change detection [17], cross-view semantic segmentation [18], spherical semantic segmentation [19] and panoramic lane marking segmentation [20]. However, most of them need several cameras to form the 360 • [16][18] [20].…”

Section: B Panoramic Segmentation Approachesmentioning

confidence: 99%

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

Yang

Chen

et al. 2019

Preprint

View full text Add to dashboard Cite

Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics. However, state-of-the-art semantic segmentation pipelines are dominantly designed to work with pinhole cameras and train with narrow Field-of-View (FoV) images. In this sense, the perception capacity is severely limited to offer higher-level of confidence for upstream navigation tasks. In this paper, we propose a network adaptation framework to achieve Panoramic Annular Semantic Segmentation (PASS), which allows to re-use conventional pinhole-view image datasets, enabling modern segmentation networks to comfortably adapt to panoramic images. Specifically, we adapt our proposed SwaftNet to enhance the sensitivity to details by implementing attention-based lateral connections between the detail-critical encoder layers and the context-critical decoder layers. We benchmark the performance of efficient segmenters on panoramic segmentation with our extended PASS dataset, demonstrating that the proposed realtime SwaftNet outperforms state-of-the-art efficient networks. Furthermore, we assess real-world performance when deploying the Detail-Sensitive PASS (DS-PASS) system on a mobile robot and an instrumented vehicle, as well as the benefit of panoramic semantics for visual odometry, showing the robustness and potential to support diverse navigational applications.

show abstract

“…For many of these applications, efficiency is critical, especially in realtime (≥30FPS) scenarios. To achieve high accuracy semantic segmentation, previous methods rely on features enhanced with rich contextual cues [13]- [17] and high-resolution spatial details [18], [19]. However, rich contextual cues are typically captured via very deep networks with sizable receptive fields [13]- [16] that require high computational costs; and detailed spatial information demand for inputs of high resolution [18], [19], which incur high FLOPs during inference.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Semantic Segmentation With Fast Attention

Perazzi

Heilbron

et al. 2021

IEEE Robot. Autom. Lett.

123

View full text Add to dashboard Cite

In deep CNN based models for semantic segmentation, high accuracy relies on rich spatial context (large receptive fields) and fine spatial details (high resolution), both of which incur high computational costs. In this paper, we propose a novel architecture that addresses both challenges and achieves state-of-the-art performance for semantic segmentation of high-resolution images and videos in real-time. The proposed architecture relies on our fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small fraction of the computational cost, by changing the order of operations. Moreover, to efficiently process high-resolution input, we apply an additional spatial reduction to intermediate feature stages of the network with minimal loss in accuracy thanks to the use of the fast attention module to fuse features. We validate our method with a series of experiments, and show that results on multiple datasets demonstrate superior performance with better accuracy and speed compared to existing approaches for real-time semantic segmentation. On Cityscapes, our network achieves 74.4% mIoU at 72 FPS and 75.5% mIoU at 58 FPS on a single Titan X GPU, which is ∼50% faster than the state-of-the-art while retaining the same accuracy.

show abstract

DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block

Cited by 27 publications

References 28 publications

Vacant Parking Slot Detection in the Around View Image Based on Deep Learning

Vacant Parking Slot Detection in the Around View Image Based on Deep Learning

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

Real-Time Semantic Segmentation With Fast Attention

Contact Info

Product

Resources

About