Multi-Modal Sensor Registration for Vehicle Perception Via Deep Neural Networks. Giering, M., Venugopalan, V., & Reddy, K. In IEEE High Performance Extreme Computing Conference (HPEC), pages 1-6, September, 2015. abstract bibtex The ability to simultaneously leverage multiple modes of sensor information is critical for perception of an automated vehicle's physical surroundings. Spatio-temporal alignment of registration of the incoming information is often a prerequisite to analyzing the fused data. The persistence and reliability of multi-modal registration is therefore the key to the stability of decision support systems ingesting the fused information. LiDAR-video systems like on those many driverless cars are a common example of where keeping the LiDAR and video channels registered to common physical features is important. We develop a deep learning method that takes multiple channels of heterogeneous data, to detect the misalignment of the LiDAR-video inputs. A number of variations were tested on the Ford LiDAR-video driving test data set and will be discussed. To the best of our knowledge the use of multi-modal deep convolutional neural networks for dynamic real-time LiDAR-video registration has not been presented.
@inproceedings{Giering2015Multi-moda,
abstract = {The ability to simultaneously leverage multiple modes of sensor information is critical for perception of an automated vehicle's physical surroundings. Spatio-temporal alignment of registration of the incoming information is often a prerequisite to analyzing the fused data. The persistence and reliability of multi-modal registration is therefore the key to the stability of decision support systems ingesting the fused information. LiDAR-video systems like on those many driverless cars are a common example of where keeping the LiDAR and video channels registered to common physical features is important. We develop a deep learning method that takes multiple channels of heterogeneous data, to detect the misalignment of the LiDAR-video inputs. A number of variations were tested on the Ford LiDAR-video driving test data set and will be discussed. To the best of our knowledge the use of multi-modal deep convolutional neural networks for dynamic real-time LiDAR-video registration has not been presented.},
author = {Giering, Michael and Venugopalan, Vivek and Reddy, Kishore},
booktitle = {IEEE High Performance Extreme Computing Conference (HPEC)},
date-added = {2020-01-20 18:26:09 -0500},
date-modified = {2020-01-20 18:26:09 -0500},
keywords = {image fusion;image registration;neural nets;optical radar;radar imaging;video signal processing;Ford LiDAR-video driving test data set;LiDAR-video input misalignment detection;LiDAR-video systems;automated vehicle physical surroundings;decision support systems;deep-learning method;driverless cars;dynamic real-time LiDAR-video registration;fused data analysis;heterogeneous data;multimodal deep-convolutional neural networks;multimodal registration persistence;multimodal registration reliability;multimodal sensor registration;multiple sensor information modes;physical features;spatio-temporal alignment;vehicle perception;Accuracy;Laser radar;Optical imaging;Optical sensors;Testing;Three-dimensional displays;Training},
month = sep,
pages = {1-6},
title = {{Multi-Modal Sensor Registration for Vehicle Perception Via Deep Neural Networks}},
year = {2015},
Bdsk-File-1 = {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},
Bdsk-Url-1 = {http://dx.doi.org/10.1109/HPEC.2015.7322485}}
Downloads: 0
{"_id":"fcfbGZBZeyioCY82C","bibbaseid":"giering-venugopalan-reddy-multimodalsensorregistrationforvehicleperceptionviadeepneuralnetworks-2015","downloads":0,"creationDate":"2016-02-09T06:00:28.648Z","title":"Multi-Modal Sensor Registration for Vehicle Perception Via Deep Neural Networks","author_short":["Giering, M.","Venugopalan, V.","Reddy, K."],"year":2015,"bibtype":"inproceedings","biburl":"https://bibbase.org/f/R3LGkkqj3uPfqr3NM/vivekv-isi-edu.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"The ability to simultaneously leverage multiple modes of sensor information is critical for perception of an automated vehicle's physical surroundings. Spatio-temporal alignment of registration of the incoming information is often a prerequisite to analyzing the fused data. The persistence and reliability of multi-modal registration is therefore the key to the stability of decision support systems ingesting the fused information. LiDAR-video systems like on those many driverless cars are a common example of where keeping the LiDAR and video channels registered to common physical features is important. We develop a deep learning method that takes multiple channels of heterogeneous data, to detect the misalignment of the LiDAR-video inputs. A number of variations were tested on the Ford LiDAR-video driving test data set and will be discussed. To the best of our knowledge the use of multi-modal deep convolutional neural networks for dynamic real-time LiDAR-video registration has not been presented.","author":[{"propositions":[],"lastnames":["Giering"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Venugopalan"],"firstnames":["Vivek"],"suffixes":[]},{"propositions":[],"lastnames":["Reddy"],"firstnames":["Kishore"],"suffixes":[]}],"booktitle":"IEEE High Performance Extreme Computing Conference (HPEC)","date-added":"2020-01-20 18:26:09 -0500","date-modified":"2020-01-20 18:26:09 -0500","keywords":"image fusion;image registration;neural nets;optical radar;radar imaging;video signal processing;Ford LiDAR-video driving test data set;LiDAR-video input misalignment detection;LiDAR-video systems;automated vehicle physical surroundings;decision support systems;deep-learning method;driverless cars;dynamic real-time LiDAR-video registration;fused data analysis;heterogeneous data;multimodal deep-convolutional neural networks;multimodal registration persistence;multimodal registration reliability;multimodal sensor registration;multiple sensor information modes;physical features;spatio-temporal alignment;vehicle perception;Accuracy;Laser radar;Optical imaging;Optical sensors;Testing;Three-dimensional displays;Training","month":"September","pages":"1-6","title":"Multi-Modal Sensor Registration for Vehicle Perception Via Deep Neural Networks","year":"2015","bdsk-file-1":"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","bdsk-url-1":"http://dx.doi.org/10.1109/HPEC.2015.7322485","bibtex":"@inproceedings{Giering2015Multi-moda,\n\tabstract = {The ability to simultaneously leverage multiple modes of sensor information is critical for perception of an automated vehicle's physical surroundings. Spatio-temporal alignment of registration of the incoming information is often a prerequisite to analyzing the fused data. The persistence and reliability of multi-modal registration is therefore the key to the stability of decision support systems ingesting the fused information. LiDAR-video systems like on those many driverless cars are a common example of where keeping the LiDAR and video channels registered to common physical features is important. We develop a deep learning method that takes multiple channels of heterogeneous data, to detect the misalignment of the LiDAR-video inputs. A number of variations were tested on the Ford LiDAR-video driving test data set and will be discussed. To the best of our knowledge the use of multi-modal deep convolutional neural networks for dynamic real-time LiDAR-video registration has not been presented.},\n\tauthor = {Giering, Michael and Venugopalan, Vivek and Reddy, Kishore},\n\tbooktitle = {IEEE High Performance Extreme Computing Conference (HPEC)},\n\tdate-added = {2020-01-20 18:26:09 -0500},\n\tdate-modified = {2020-01-20 18:26:09 -0500},\n\tkeywords = {image fusion;image registration;neural nets;optical radar;radar imaging;video signal processing;Ford LiDAR-video driving test data set;LiDAR-video input misalignment detection;LiDAR-video systems;automated vehicle physical surroundings;decision support systems;deep-learning method;driverless cars;dynamic real-time LiDAR-video registration;fused data analysis;heterogeneous data;multimodal deep-convolutional neural networks;multimodal registration persistence;multimodal registration reliability;multimodal sensor registration;multiple sensor information modes;physical features;spatio-temporal alignment;vehicle perception;Accuracy;Laser radar;Optical imaging;Optical sensors;Testing;Three-dimensional displays;Training},\n\tmonth = sep,\n\tpages = {1-6},\n\ttitle = {{Multi-Modal Sensor Registration for Vehicle Perception Via Deep Neural Networks}},\n\tyear = {2015},\n\tBdsk-File-1 = {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},\n\tBdsk-Url-1 = {http://dx.doi.org/10.1109/HPEC.2015.7322485}}\n\n","author_short":["Giering, M.","Venugopalan, V.","Reddy, K."],"bibbaseid":"giering-venugopalan-reddy-multimodalsensorregistrationforvehicleperceptionviadeepneuralnetworks-2015","role":"author","urls":{},"keyword":["image fusion;image registration;neural nets;optical radar;radar imaging;video signal processing;Ford LiDAR-video driving test data set;LiDAR-video input misalignment detection;LiDAR-video systems;automated vehicle physical surroundings;decision support systems;deep-learning method;driverless cars;dynamic real-time LiDAR-video registration;fused data analysis;heterogeneous data;multimodal deep-convolutional neural networks;multimodal registration persistence;multimodal registration reliability;multimodal sensor registration;multiple sensor information modes;physical features;spatio-temporal alignment;vehicle perception;Accuracy;Laser radar;Optical imaging;Optical sensors;Testing;Three-dimensional displays;Training"],"metadata":{"authorlinks":{}}},"search_terms":["multi","modal","sensor","registration","vehicle","perception","via","deep","neural","networks","giering","venugopalan","reddy"],"keywords":["image fusion;image registration;neural nets;optical radar;radar imaging;video signal processing;ford lidar-video driving test data set;lidar-video input misalignment detection;lidar-video systems;automated vehicle physical surroundings;decision support systems;deep-learning method;driverless cars;dynamic real-time lidar-video registration;fused data analysis;heterogeneous data;multimodal deep-convolutional neural networks;multimodal registration persistence;multimodal registration reliability;multimodal sensor registration;multiple sensor information modes;physical features;spatio-temporal alignment;vehicle perception;accuracy;laser radar;optical imaging;optical sensors;testing;three-dimensional displays;training"],"authorIDs":[],"dataSources":["MhetGwzdnqQv3dJWT","i5A8jKqyW67R7nn75","oodiEqv3HQNeZtGeC"]}