Parallel Complement Network for Real-Time Semantic Segmentation of Road Scenes

Lv, Qingxuan; Sun, Xin; Chen, Changrui; Dong, Junyu; Zhou, Huiyu

doi:10.1109/tits.2020.3044672

Cited by 34 publications

(12 citation statements)

References 58 publications

(133 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare the segmentation effect of the proposed algorithm with other networks, we trained UNet, UperNet, 27 Fast_SCNN, 28 ICNet, 29 HRNet, 30 PCNet, 31 PTIA-Net, 32 EARNet, 33 and DeepLabv3+ on the Cityscapes dataset under the same data preprocessing, hyperparameters, and other settings; and the performance of the algorithms was compared using the mIOU, PA, and MPA metrics. The results are shown in Table 5.…”

Section: Comparison Experimentsmentioning

confidence: 99%

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

et al. 2022

View full text Add to dashboard Cite

. Semantic scene segmentation has become an important application in computer vision and is an essential part of intelligent transportation systems for complete scene understanding of the surrounding environment. Several methods based on convolutional neural networks have emerged, but they have some problems, including small-scale target loss, inaccurate detailed region segmentation, and boundary category confusion. Using shallow features, we exploit the capabilities of global context information according to the theory of pyramids. A weighted pyramid feature fusion module is constructed to fuse the feature maps of different scales generated by the backbone network, and the proportion of feature fusion is dynamically updated by trainable parameters. After that, a self-attention mechanism is introduced to discover information about spatial channel interdependencies. Finally, the atrous spatial pyramid pooling module of the DeepLabv3+ network is improved by connecting the atrous convolution with different dilation rates at the receptive field. The experimental results show 4.1% mean pixel accuracy and 3.92% mean intersection over union improvements in the proposed method compared with the DeepLabv3+, and the result of semantic segmentation is more accurate.

show abstract

Section: Comparison Experimentsmentioning

confidence: 99%

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Adopting high-resolution inputs and features [7] [8], multiscale processing [9] [10], spatial and semantic reasoning [11] [12] [13], local and global context aggregation [4] [5] [14], as well as different strategies of feature fusion [2] [15] [16] are some of the most common strategies.…”

Section: Introductionmentioning

confidence: 99%

A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design

Manfio¹,

Osório²

2023

Preprint

View full text Add to dashboard Cite

Semantic image and video segmentation stand among the most important tasks in computer vision nowadays, since they provide a complete and meaningful representation of the environment by means of a dense classification of the pixels in a given scene. Recently, Deep Learning, and more precisely Convolutional Neural Networks, have boosted semantic segmentation to a new level in terms of performance and generalization capabilities. However, designing Deep Semantic Segmentation models is a complex task, as it may involve application-dependent aspects. Particularly, when considering autonomous driving applications, the robustness-efficiency tradeoff, as well as intrinsic limitations -computational/memory bounds and data-scarcity -and constraints -real-time inference -should be taken into consideration. In this respect, the use of additional data modalities, such as depth perception for reasoning on the geometry of a scene, and temporal cues from videos to explore redundancy and consistency, are promising directions yet not explored to their full potential in the literature. In this paper, we conduct a survey on the most relevant and recent advances in Deep Semantic Segmentation in the context of vision for autonomous vehicles, from three different perspectives: efficiency-oriented model development for real-time operation, RGB-Depth data integration (RGB-D semantic segmentation), and the use of temporal information from videos in temporalaware models. Our main objective is to provide a comprehensive discussion on the main methods, advantages, limitations, results and challenges faced from each perspective, so that the reader can not only get started, but also be up to date in respect to recent advances in this exciting and challenging research field.

show abstract

“…Therefore, these methods may not be the best option for solving the sensorimotor control task. MPs also need significant quantities of labeled data, which may be difficult to come by, such as pixel-wise semantic segmentation [7,8] for neural network training, or high-definition maps for localization. Traffic sign recognition [9], obstacle detection [10][11][12][13], lane line recognition [14][15][16][17], monocular depth estimation [18][19][20], SLAM and positions recognition [21][22][23], and other sub-tasks, also become challenges for MPs methods.…”

Section: Introductionmentioning

confidence: 99%

Navigating an Automated Driving Vehicle via the Early Fusion of Multi-Modality

Haris

Głowacz

2022

Sensors

View full text Add to dashboard Cite

The ability of artificial intelligence to drive toward an intended destination is a key component of an autonomous vehicle. Different paradigms are now being employed to address artificial intelligence advancement. On the one hand, modular pipelines break down the driving model into submodels, such as perception, maneuver planning and control. On the other hand, we used the end-to-end driving method to assign raw sensor data directly to vehicle control signals. The latter is less well-studied but is becoming more popular since it is easier to use. This article focuses on end-to-end autonomous driving, using RGB pictures as the primary sensor input data. The autonomous vehicle is equipped with a camera and active sensors, such as LiDAR and Radar, for safe navigation. Active sensors (e.g., LiDAR) provide more accurate depth information than passive sensors. As a result, this paper examines whether combining the RGB from the camera and active depth information from LiDAR has better results in end-to-end artificial driving than using only a single modality. This paper focuses on the early fusion of multi-modality and demonstrates how it outperforms a single modality using the CARLA simulator.

show abstract

Parallel Complement Network for Real-Time Semantic Segmentation of Road Scenes

Cited by 34 publications

References 58 publications

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design

Navigating an Automated Driving Vehicle via the Early Fusion of Multi-Modality

Contact Info

Product

Resources

About