Distance to obstacle detection in autonomous machine applications
In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such...
Gespeichert in:
Hauptverfasser: | , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Herrera Castro, Daniel Oh, Sangmin Park, Minwoo Janis, Pekka Yang, Yilin Nister, David Jujjavarapu, Bala Siva Sashank Ye, Zhaoting Koivisto, Tommi |
description | In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters-such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11308338B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11308338B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11308338B23</originalsourceid><addsrcrecordid>eNqNyjEKAkEMQNFpLES9QzyA4DrNtuqu2Kv1EmPEwGwykOz9VfAAVv8Xb572nXigEkMY2P3zVBgeHEwhpiAKOIWpjTY5jEgvUQastQjhV_gyzZ5YnFe_LtL61F-P5w1XG9grEivHcLs0Td62ObeHXf7HvAE9HzJZ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Distance to obstacle detection in autonomous machine applications</title><source>esp@cenet</source><creator>Herrera Castro, Daniel ; Oh, Sangmin ; Park, Minwoo ; Janis, Pekka ; Yang, Yilin ; Nister, David ; Jujjavarapu, Bala Siva Sashank ; Ye, Zhaoting ; Koivisto, Tommi</creator><creatorcontrib>Herrera Castro, Daniel ; Oh, Sangmin ; Park, Minwoo ; Janis, Pekka ; Yang, Yilin ; Nister, David ; Jujjavarapu, Bala Siva Sashank ; Ye, Zhaoting ; Koivisto, Tommi</creatorcontrib><description>In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters-such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220419&DB=EPODOC&CC=US&NR=11308338B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220419&DB=EPODOC&CC=US&NR=11308338B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Herrera Castro, Daniel</creatorcontrib><creatorcontrib>Oh, Sangmin</creatorcontrib><creatorcontrib>Park, Minwoo</creatorcontrib><creatorcontrib>Janis, Pekka</creatorcontrib><creatorcontrib>Yang, Yilin</creatorcontrib><creatorcontrib>Nister, David</creatorcontrib><creatorcontrib>Jujjavarapu, Bala Siva Sashank</creatorcontrib><creatorcontrib>Ye, Zhaoting</creatorcontrib><creatorcontrib>Koivisto, Tommi</creatorcontrib><title>Distance to obstacle detection in autonomous machine applications</title><description>In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters-such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEKAkEMQNFpLES9QzyA4DrNtuqu2Kv1EmPEwGwykOz9VfAAVv8Xb572nXigEkMY2P3zVBgeHEwhpiAKOIWpjTY5jEgvUQastQjhV_gyzZ5YnFe_LtL61F-P5w1XG9grEivHcLs0Td62ObeHXf7HvAE9HzJZ</recordid><startdate>20220419</startdate><enddate>20220419</enddate><creator>Herrera Castro, Daniel</creator><creator>Oh, Sangmin</creator><creator>Park, Minwoo</creator><creator>Janis, Pekka</creator><creator>Yang, Yilin</creator><creator>Nister, David</creator><creator>Jujjavarapu, Bala Siva Sashank</creator><creator>Ye, Zhaoting</creator><creator>Koivisto, Tommi</creator><scope>EVB</scope></search><sort><creationdate>20220419</creationdate><title>Distance to obstacle detection in autonomous machine applications</title><author>Herrera Castro, Daniel ; Oh, Sangmin ; Park, Minwoo ; Janis, Pekka ; Yang, Yilin ; Nister, David ; Jujjavarapu, Bala Siva Sashank ; Ye, Zhaoting ; Koivisto, Tommi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11308338B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Herrera Castro, Daniel</creatorcontrib><creatorcontrib>Oh, Sangmin</creatorcontrib><creatorcontrib>Park, Minwoo</creatorcontrib><creatorcontrib>Janis, Pekka</creatorcontrib><creatorcontrib>Yang, Yilin</creatorcontrib><creatorcontrib>Nister, David</creatorcontrib><creatorcontrib>Jujjavarapu, Bala Siva Sashank</creatorcontrib><creatorcontrib>Ye, Zhaoting</creatorcontrib><creatorcontrib>Koivisto, Tommi</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Herrera Castro, Daniel</au><au>Oh, Sangmin</au><au>Park, Minwoo</au><au>Janis, Pekka</au><au>Yang, Yilin</au><au>Nister, David</au><au>Jujjavarapu, Bala Siva Sashank</au><au>Ye, Zhaoting</au><au>Koivisto, Tommi</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Distance to obstacle detection in autonomous machine applications</title><date>2022-04-19</date><risdate>2022</risdate><abstract>In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters-such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng |
recordid | cdi_epo_espacenet_US11308338B2 |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
title | Distance to obstacle detection in autonomous machine applications |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A35%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Herrera%20Castro,%20Daniel&rft.date=2022-04-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11308338B2%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |