{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:31:43Z","timestamp":1753893103826,"version":"3.41.2"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T00:00:00Z","timestamp":1749686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Obstacle avoidance is important for autonomous driving. Metric scale obstacle detection using a monocular camera for obstacle avoidance has been studied. In this study, metric scale obstacle detection means detecting obstacles and measuring the distance to them with a metric scale. We have already developed PMOD-Net, which realizes metric scale obstacle detection by using a monocular camera and a 3D map for autonomous driving. However, PMOD-Net\u2019s distance error of non-fixed obstacles that do not exist on the 3D map is large. Accordingly, this study deals with the problem of improving distance estimation of non-fixed obstacles for obstacle avoidance. To solve the problem, we focused on the fact that PMOD-Net simultaneously performed object detection and distance estimation. We have developed a new loss function called \u201cDifSeg.\u201d DifSeg is calculated from the distance estimation results on the non-fixed obstacle region, which is defined based on the object detection results. Therefore, DifSeg makes PMOD-Net focus on non-fixed obstacles during training. We evaluated the effect of DifSeg by using CARLA simulator, KITTI, and an original indoor dataset. The evaluation results showed that the distance estimation accuracy was improved on all datasets. Especially in the case of KITTI, the distance estimation error of our method was 2.42 m, which was 2.14 m less than that of the latest monocular depth estimation method.<\/jats:p>","DOI":"10.3389\/frobt.2025.1560342","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T10:15:39Z","timestamp":1749723339000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Metric scale non-fixed obstacles distance estimation using a 3D map and a monocular camera"],"prefix":"10.3389","volume":"12","author":[{"given":"Daijiro","family":"Higashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Fukuta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsuyoshi","family":"Tasaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,12]]},"reference":[{"key":"B1","first-page":"2743","article-title":"The normal distributions transform: a new approach to laser scan matching","volume-title":"International conference on intelligent robots and systems","author":"Biber","year":"2003"},{"key":"B2","first-page":"1926","article-title":"Cmrnet: camera to lidar-map registration","volume-title":"International conference on intelligent robots and systems","author":"Cattaneo","year":"2016"},{"article-title":"Carla: an open urban driving simulator","year":"2017","author":"[Dataset] Dosovitskiy","key":"B3"},{"key":"B5","first-page":"167","article-title":"Efficient graph-based image segmentation","volume-title":"International journal of computer vision","author":"Felzenszwalb","year":"2004"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1109\/cvpr.2012.6248074","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"B6","first-page":"263","article-title":"Context-enhanced stereo transformer","volume-title":"European conference on computer vision","author":"Guo","year":"2022"},{"key":"B7","first-page":"21653","article-title":"Virtual sparse convolution for multimodal 3d object detection","volume-title":"Computer vision and pattern recognition conference","author":"Hai","year":"2023"},{"key":"B8","first-page":"3828","article-title":"Bi-directional cascade network for perceptual edge detection","volume-title":"Computer vision and pattern recognition conference","author":"He","year":"2019"},{"key":"B9","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1080\/23307706.2022.2065370","article-title":"Object servoing of differential-drive service robots using switched control","volume":"10","author":"Jia","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.07436","article-title":"Global-local path networks for monocular depth estimation with vertical cutdepth","author":"Kim","year":"2022","journal-title":"arXiv Prepr. arXiv:2201.07436"},{"key":"B11","first-page":"126","article-title":"Depth-assisted real-time 3d object detection for augmented reality","volume-title":"International conference on advanced technologies","author":"Lee","year":"2011"},{"key":"B12","first-page":"16263","article-title":"Practical stereo matching via cascaded recurrent network with adaptive correlation","volume-title":"Computer vision and pattern recognition conference","author":"Li","year":"2022"},{"article-title":"Kitti-360: a novel dataset and benchmarks for urban scene understanding in 2d and 3d","year":"2022","author":"Liao","key":"B13"},{"key":"B14","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"Labelme: a database and web-based tool for image annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"B15","first-page":"4510","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","volume-title":"Computer vision and pattern recognition conference","author":"Sandler","year":"2018"},{"key":"B16","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1080\/01691864.2022.2153080","article-title":"Pmod-net: point-cloud-map-based metric scale obstacle detection by using a monocular camera","volume":"37","author":"Shikishima","year":"2023","journal-title":"Adv. Robot."},{"key":"B17","doi-asserted-by":"publisher","first-page":"8883","DOI":"10.1109\/tpami.2024.3411571","article-title":"Nddepth: normal-distance assisted monocular depth estimation and completion","volume":"46","author":"Shuwei","year":"2024","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B18","first-page":"53025","article-title":"Iebins: iterative elastic bins for monocular depth estimation","volume-title":"Advances in neural information processing systems","author":"Shuwei","year":"2023"},{"key":"B19","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","article-title":"Indoor segmentation and support inference from rgbd images","author":"Silberman","year":"2012"},{"key":"B20","first-page":"7276","article-title":"Mvx-net: multimodal voxelnet for 3d object detection","volume-title":"International conference on robotics and automation","author":"Sindagi","year":"2019"},{"key":"B21","first-page":"11794","article-title":"Pointaugmenting: cross-modal augmentation for 3d object detection","volume-title":"Computer vision and pattern recognition conference","author":"Wang","year":"2021"},{"article-title":"Revealing the dark secrets of masked image modeling","year":"2022","author":"Xie","key":"B22"},{"key":"B23","first-page":"10371","article-title":"Depth anything: unleashing the power of large-scale unlabeled data","volume-title":"Computer vision and pattern recognition conference","author":"Yang","year":"2024"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1560342\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T10:15:44Z","timestamp":1749723344000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1560342\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,12]]},"references-count":23,"alternative-id":["10.3389\/frobt.2025.1560342"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1560342","relation":{},"ISSN":["2296-9144"],"issn-type":[{"type":"electronic","value":"2296-9144"}],"subject":[],"published":{"date-parts":[[2025,6,12]]},"article-number":"1560342"}}