Handbook of Robotics 2nd edition, Chapter 62 on "Intelligent Vehicles, Handbook of Robotics 2nd Edition, pp.1627-1656, 2016. ,
URL : https://hal.archives-ouvertes.fr/hal-01260280
Development of small robot for home floor cleaning, SICE 2002. Proceedings of the 41st SICE Annual Conference, vol.5, p.1, 2002. ,
Multiple 3D object tracking for augmented reality, Proceedings of the 7th IEEE/ACM International Symposium on Mixed and Augmented Reality, pp.117-120, 2008. ,
, Point clouds". In: Photogrammetric Engineering & Remote Sensing, vol.76, p.1, 2010.
Hybrid Sampling Bayesian Occupancy Filter, IEEE Intelligent Vehicles Symposium (IV), p.1, 2014. ,
Conditional Monte Carlo Dense Occupancy Tracker, 18th IEEE International Conference on Intelligent Transportation Systems. Las Palmas, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01205298
From Proxemics Theory to Socially-Aware Navigation: A Survey, International Journal of Social Robotics, vol.7, issue.2, pp.137-153, 2015. ,
URL : https://hal.archives-ouvertes.fr/hal-01067278
Semantic Grid Estimation with a Hybrid Bayesian and Deep Neural Network Approach, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01881377
Are cars just 3d boxes?-jointly estimating the 3d shape of multiple objects, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3678-3685, 2014. ,
Complex-YOLO: Real-time 3D Object Detection on Point Clouds, p.3, 2018. ,
Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud, 2017. ,
Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks, 2017 IEEE International Conference on, pp.1355-1361, 2017. ,
Voxnet: A 3d convolutional neural network for real-time object recognition, Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on, p.3, 2015. ,
Octnet: Learning deep 3d representations at high resolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol.3, p.3, 2017. ,
O-cnn: Octree-based convolutional neural networks for 3d shape analysis, ACM Transactions on Graphics (TOG), vol.36, issue.4, p.3, 2017. ,
Monocular 3d object detection for autonomous driving, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2147-2156, 2016. ,
Multi-view 3d object detection network for autonomous driving, IEEE CVPR, vol.1, p.41, 2017. ,
Pointnet: Deep learning on point sets for 3d classification and segmentation, Proc. Computer Vision and Pattern Recognition (CVPR) ,
Pointnet++: Deep hierarchical feature learning on point sets in a metric space, Advances in Neural Information Processing Systems, pp.5099-5108, 2017. ,
Pointwise convolutional neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol.4, p.35, 2018. ,
PointCNN, vol.4, 2018. ,
Exploring spatial context for 3d semantic segmentation of point clouds, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.716-724, 2017. ,
Frustum PointNets for 3D Object Detection From RGB-D Data, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. ,
Voxelnet: End-to-end learning for point cloud based 3d object detection, 2017. ,
, 3D Point Cloud Classification using Deep Learning -Recent Works
Spatial transformer networks, Advances in neural information processing systems, pp.2017-2025, 2015. ,
Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems, p.13, 2015. ,
You only look once: Unified, real-time object detection, Proceedings of the IEEE conference on computer vision and pattern recognition, p.14, 2016. ,
Ssd: Single shot multibox detector, European conference on computer vision, p.14, 2016. ,
Analyzing vision at the complexity level, Behavioral and brain sciences, vol.13, pp.423-445, 1990. ,
The dynamic representation of scenes. Visual Cognition7: 1742. Visual search for change: A probe into the nature of attentional processing, Visual Cognition, vol.7, p.14, 2000. ,
Recurrent models of visual attention, Advances in neural information processing systems, pp.2204-2212, 2014. ,
Multiple object recognition with visual attention, 2014. ,
Enriched deep recurrent visual attention model for multiple object recognition, Applications of Computer Vision (WACV, vol.25, pp.17-19, 2017. ,
Recurrent spatial transformer networks, vol.37, pp.17-19, 2015. ,
Draw: A recurrent neural network for image generation, p.19, 2015. ,
, Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. cite arxiv:1412.3555Comment: Presented in NIPS 2014 Deep Learning and Representation Learning Workshop, p.19, 2014.
Glimpse clouds: Human activity recognition from unstructured feature points, Computer Vision and Pattern Recognition (CVPR), vol.3, p.19, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01713109
SurfConv: Bridging 3D and 2D Convolution for RGBD Images, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.25, 2018. ,
Attentional ShapeCon-textNet for Point Cloud Recognition, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p.25, 2018. ,
3d shapenets: A deep representation for volumetric shapes, Proceedings of the IEEE conference on computer vision and pattern recognition, p.29, 2015. ,
Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite, Conference on Computer Vision and Pattern Recognition (CVPR). 2012 (cit, vol.41, p.30 ,
3d object proposals for accurate object class detection, Advances in Neural Information Processing Systems, p.42, 2015. ,
3D fully convolutional network for vehicle detection in point cloud, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), p.42, 2017. ,
2 2.1 (a) Shows the principle of working of LiDAR; (b) Typical point cloud generated by high-definition LiDAR; (c) Point cloud generated from stereo cameras, Multiple object detection in 3D point clouds ,
12 2.5 (a)Spherical point-wise convolution operator centred at different points in a point cloud; (b) Convolutions in images; (c) Pointwise kernel and subdomains; Images reproduced from ACFR dataset and guide to arithmetic convolution ,
16 2.9 Architecture of Spatial Transformer Network ,
20 3.2 Architecture of Context Network; MLP -Multi-Layer Perceptron 21 ,
, 2D illustration of working of 3D Transformer, p.24
Sample images of cluttered MNIST dataset, p.28 ,
Sample images of ModelNet40 [41, p.29 ,
30 4.4 30m x 30m Working area in blue rectangle, 10m x 10m crops in red squares ,
each cropped region has 3 bounding boxes. The green bounding boxes represent the locations of car and red bounding boxes are random locations of non-car regions, p.32 ,
, Autonomous vehicle platform
, Shows partitioning of point cloud by PointWise kernel into subdomains represented by different color. Points within a subdomain share same weight, ModelNet40 dataset, p.37
, Recurrent-STN Network with supervised localization, p.38
, Recurrent-STN Network without supervised localization, p.38
Each row shows a sequence of the predictions by the network. First four rows illustrates scenarios where network successfully identified and localised the car. Whereas last two rows shows failure cases, p.44 ,
, Attentional PointNet on Team Chroma Inria dataset, vol.45
, 36 5.2 Performance comparison in 3D detection: average precision (in %) on KITTI validation set. BV -Birdeye View