Lane Detection in Low-light Conditions Using an Efficient Data Enhancement: Light Conditions Style Transfer

Liu, Tong; Chen, Zhaowei; Yang, Yi; Wu, Zehao; Li, Haowei

doi:10.1109/iv47402.2020.9304613

Cited by 68 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effects of our model, we undertook a broad comparison with several state-of-the-art methods. We evaluated Nb_SINet and multiple backbones, i.e., ENet_LGAD [ 15 ], SIM_CycleGAN+ERFNet [ 16 ], ERFNet-E2E [ 17 ], ERFNet_VP [ 18 ] and ERFNet-HESA [ 19 ], for each scenario, and the mean F1 for each method is also shown in Table 5 .…”

Section: Methodsmentioning

confidence: 99%

“…However, substantial computational resources are required to train the teacher network. Liu et al [ 16 ] presented style transformation for data augmentation to generate images in low-light conditions with generative adversarial networks that improve the environmental adaptability of the lane detector, which does not demand any additional manual annotation or inference overhead. Yun et al [ 17 ] used the horizontal reduction module to compactly extract the lane marker information in the image and achieved end-to-end lane marker detection via row-wise classification.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Real-time lane detection model based on non bottleneck skip residual connections and attention pyramids

et al. 2021

View full text Add to dashboard Cite

The security of car driving is of interest due to the growing number of motor vehicles and frequent occurrence of road traffic accidents, and the combination of advanced driving assistance system (ADAS) and vehicle-road cooperation can prevent more than 90% of traffic accidents. Lane detection, as a vital part of ADAS, has poor real-time performance and accuracy in multiple scenarios, such as road damage, light changes, and traffic jams. Moreover, the sparse pixels of lane lines on the road pose a tremendous challenge to the task of lane line detection. In this study, we propose a model that fuses non bottleneck skip residual connections and an improved attention pyramid (IAP) to effectively obtain contextual information about real-time scenes and improve the robustness and real-time performance of current lane detection models. The proposed model modifies the efficient residual factorized pyramid scene parsing network (ERF-PSPNet) and utilizes skip residual connections in non bottleneck-1D modules. A decoder with an IAP provides high-level feature maps with pixel-level attention. We add an auxiliary segmenter and a lane predictor side-by-side after the encoder, the former for lane prediction and the latter to assist with semantic segmentation for classification purposes, as well as to solve the gradient disappearance problem. On the CULane dataset, the F1 metric reaches 92.20% in the normal scenario, and the F1 metric of the model is higher than the F1 metrics of other existing models, such as ERFNet-HESA, ENet_LGAD, and DSB+LDCDI, in normal, crowded, night, dazzling light and no line scenarios; in addition, the mean F1 of the nine scenarios reached 74.10%, the runtime (time taken to test 100 images) of the model was 5.88 ms, and the number of parameters was 2.31M, which means that the model achieves a good trade-off between real-time performance and accuracy compared to the current best results (i.e., a running time of 13.4 ms and 0.98M parameters).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Real-time lane detection model based on non bottleneck skip residual connections and attention pyramids

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In crowded, dazzle, no line, cross, and night scenarios, FANet outperforms the other methods. Compared with SIM-CycleGAN [ 39 ], although it is specifically designed for different scenarios, FANet is also close to it in many metrics, or even better. Compared with the knowledge distillation method IntRA-KD [ 14 ] and the network search method CurveLanes-NAS [ 40 ], FANet has a higher F1 score of 3.09% and 4.09% F1 respectively.…”

Section: Methodsmentioning

confidence: 99%

Fast and Accurate Lane Detection via Graph Structure and Disentangled Representation Learning

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

It is desirable to maintain high accuracy and runtime efficiency at the same time in lane detection. However, due to the long and thin properties of lanes, extracting features with both strong discrimination and perception abilities needs a huge amount of calculation, which seriously slows down the running speed. Therefore, we design a more efficient way to extract the features of lanes, including two phases: (1) Local feature extraction, which sets a series of predefined anchor lines, and extracts the local features through their locations. (2) Global feature aggregation, which treats local features as the nodes of the graph, and builds a fully connected graph by adaptively learning the distance between nodes, the global feature can be aggregated through weighted summing finally. Another problem that limits the performance is the information loss in feature compression, mainly due to the huge dimensional gap, e.g., from 512 to 8. To handle this issue, we propose a feature compression module based on decoupling representation learning. This module can effectively learn the statistical information and spatial relationships between features. After that, redundancy is greatly reduced and more critical information is retained. Extensional experimental results show that our proposed method is both fast and accurate. On the Tusimple and CULane benchmarks, with a running speed of 248 FPS, F1 values of 96.81% and 75.49% were achieved, respectively.

show abstract

“…Content may change prior to final publication. FIGURE 2: Preprocessing a marked road of smoothing filters, image enhancement has been done in some researches in order to retain contour details [28]- [30].…”

Section: ) Image Smoothing Sharpening and Shadow Removalmentioning

confidence: 99%

Steering Angle Prediction Techniques for Autonomous Ground Vehicles: A Review

et al. 2021

View full text Add to dashboard Cite

Unintentional lane departure accidents are one of the biggest reasons for the causalities that occur due to human errors. By incorporating lane-keeping features in vehicles, many accidents can be avoided. The lane-keeping system operates by auto-steering the vehicle in order to keep it within the desired lane, despite of changes in road conditions and other interferences. Accurate steering angle prediction is crucial to keep the vehicle within the road boundaries, which is a challenging task. The main difficulty in this regard is to identify the drivable road area on heterogeneous road types varying in color, texture, illumination conditions, and lane marking types. This strenuous problem can be addressed by two approaches, namely, 'computer-vision-based approach' and 'imitation-learning-based approach'. To the best of our knowledge, at present, there is no such detailed review study covering both the approaches and their related optimization techniques. This comprehensive review attempts to provide a clear picture of both approaches of steering angle prediction in the form of step by step procedures. The taxonomy of steering angle prediction has been presented in the paper for a better comprehension of the problem. We have also discussed open research problems at the end of the paper to help the researchers of this area to discover new research horizons.

show abstract

Lane Detection in Low-light Conditions Using an Efficient Data Enhancement: Light Conditions Style Transfer

Cited by 68 publications

References 17 publications

Real-time lane detection model based on non bottleneck skip residual connections and attention pyramids

Real-time lane detection model based on non bottleneck skip residual connections and attention pyramids

Fast and Accurate Lane Detection via Graph Structure and Disentangled Representation Learning

Steering Angle Prediction Techniques for Autonomous Ground Vehicles: A Review

Contact Info

Product

Resources

About