Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds

Zhang, Wenjun; Luo, Wenjie; Urtasun, Raquel

doi:10.1109/3dv.2018.00053

Cited by 78 publications

(55 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation of our proposed method on the task of 3D semantic segmentation compared to the existing stateof-the-art is shown in Table 2. To assess the methods, we use the mean class accuracy (mAcc), the mean class IoU (mIoU), and the per-class IoU computed over the LiDAR points as defined in [34]. To perform semantic segmentation, we classify each point in the LiDAR image with its most likely class according to the predicted class probabilities.…”

Section: D Semantic Segmentationmentioning

confidence: 99%

“…Since the resolution of the image is approximately the resolution of the LiDAR, it is uncommon for multiple points to occupy the same cell. For comparisons, we implement the method proposed in [34], and we incorporate focal loss [16] into their method to improve performance.…”

Section: D Semantic Segmentationmentioning

confidence: 99%

“…motorcycle). Again, we believe this is due to our approach using a RV instead of the BEV representation used in the previous work [34]. The BEV voxelizes the 3D points, so precise segmentation of small objects is challenging.…”

Section: D Semantic Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Meyer

Charland

Hegde

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

144

View full text Add to dashboard Cite

In this paper, we present an extension to LaserNet, an efficient and state-of-the-art LiDAR based 3D object detector. We propose a method for fusing image data with the LiDAR data and show that this sensor fusion method improves the detection performance of the model especially at long ranges. The addition of image data is straightforward and does not require image labels. Furthermore, we expand the capabilities of the model to perform 3D semantic segmentation in addition to 3D object detection. On a large benchmark dataset, we demonstrate our approach achieves state-of-the-art performance on both object detection and semantic segmentation while maintaining a low runtime.

show abstract

Section: D Semantic Segmentationmentioning

confidence: 99%

Section: D Semantic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Meyer

Charland

Hegde

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

144

View full text Add to dashboard Cite

show abstract

“…Our inferred monocular plan view representation has some similarities with occupancy grids generated by LiDAR sensors: we contrast free space with space occupied by vehicles and pedestrians. Recent works have used convolutional networks with LiDAR data for localization [12], scene flow estimation [13], 3D detection and tracking [14]- [20], intention prediction [21], and semantic segmentation [22]. In particular, Luo et al propose a joint framework for 3D detection, tracking, and motion forecasting via 3D convolution over a bird's eye view representation of 3D world [15].…”

Section: Related Workmentioning

confidence: 99%

Monocular Plan View Networks for Autonomous Driving

Wang

Devin

Cai³

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan view, for end-to-end control. We detect vehicles and pedestrians in the first person view and project them into an overhead plan view. This representation provides an abstraction of the environment from which a deep network can easily deduce the positions and directions of entities. Additionally, the plan view enables us to leverage advances in 3D object detection in conjunction with deep policy learning. We evaluate our monocular plan view network on the photo-realistic Grand Theft Auto V simulator. A network using both a plan view and front view causes less than half as many collisions as previous detection-based methods and an order of magnitude fewer collisions than pure pixel-based policies.

show abstract

“…Similarly, to [19], the detection problem addressed in this work operates with a class-imbalanced data in which each radar data frame contains significantly larger amount of non- detection bins than any other classes. Therefore, this work uses the class-balanced cross-entropy loss in the RD-Net.…”

Section: Loss Functionsmentioning

confidence: 99%

Deep Radar Detector

Brodeski

Bilik²,

Giryes

2019

2019 IEEE Radar Conference (RadarConf)

View full text Add to dashboard Cite

While camera and LiDAR processing have been revolutionized since the introduction of deep learning, radar processing still relies on classical tools. In this paper, we introduce a deep learning approach for radar processing, working directly with the radar complex data. To overcome the lack of radar labeled data, we rely in training only on the radar calibration data and introduce new radar augmentation techniques. We evaluate our method on the radar 4D detection task and demonstrate superior performance compared to the classical approaches while keeping real-time performance. Applying deep learning on radar data has several advantages such as eliminating the need for an expensive radar calibration process each time and enabling classification of the detected objects with almost zero-overhead.

show abstract

Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds

Cited by 78 publications

References 22 publications

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Monocular Plan View Networks for Autonomous Driving

Deep Radar Detector

Contact Info

Product

Resources

About