{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:05:12Z","timestamp":1783569912652,"version":"3.55.0"},"reference-count":34,"publisher":"SAGE Publications","issue":"1-2","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring, and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains\u2014the first being coastal waters\u2014with many obstacles, structures, and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, long wave infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2900 LWIR segmented images captured in coastal maritime environment over a period of 2\u00a0years. The images are labeled using instance segmentation and classified into seven categories\u2014sky, water, obstacle, living obstacle, bridge, self, and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain, it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.<\/jats:p>","DOI":"10.1177\/02783649231153020","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T22:25:19Z","timestamp":1678141519000},"page":"21-32","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":27,"title":["MassMIND: Massachusetts Maritime INfrared Dataset"],"prefix":"10.1177","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0459-3424","authenticated-orcid":false,"given":"Shailesh","family":"Nirgudkar","sequence":"first","affiliation":[{"name":"University of Massachusetts, Lowell, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6214-0103","authenticated-orcid":false,"given":"Michael","family":"DeFilippo","sequence":"additional","affiliation":[{"name":"MIT Sea Grant, Autonomous Underwater Vehicles Lab, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Sacarny","sequence":"additional","affiliation":[{"name":"MIT Sea Grant, Autonomous Underwater Vehicles Lab, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Benjamin","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology Laboratory for Autonomous Marine Sensing Systems, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Robinette","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Lowell, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2023,3,6]]},"reference":[{"key":"bibr1-02783649231153020","unstructured":"AUVLab (1989) MIT Sea Grant. Autonomous Underwater Vehicles Lab URL https:\/\/seagrant.mit.edu\/auv-lab\/"},{"key":"bibr2-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2015.7301727"},{"key":"bibr3-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197194"},{"key":"bibr4-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967909"},{"key":"bibr5-02783649231153020","volume-title":"MODS- A USV-Oriented Object Detection and Obstacle Segmentation Benchmark","author":"Bovcon B","year":"2021"},{"key":"bibr7-02783649231153020","doi-asserted-by":"publisher","DOI":"10.17632\/gtt7stf5x8.2"},{"key":"bibr8-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"bibr10-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"bibr11-02783649231153020","first-page":"10","volume":"27","author":"Csurka G","year":"2013","journal-title":"Bmvc"},{"key":"bibr12-02783649231153020","unstructured":"Debals O (2021) Platform for Image Segmentation URL https:\/\/segments.ai."},{"key":"bibr13-02783649231153020","volume-title":"RoboWhaler: A Robotic Vessel for Marine Autonomy and Dataset Collection","author":"DeFilippo M","year":"2021"},{"key":"bibr14-02783649231153020","first-page":"248","author":"Deng J","year":"2009","journal-title":"CVPR"},{"key":"bibr15-02783649231153020","unstructured":"Edmund Optics (2022). What is SWIR? URL https:\/\/www.edmundoptics.com\/knowledge-center\/application-notes\/imaging\/what-is-swir\/?utm_medium=email&utm_source=transaction"},{"key":"bibr16-02783649231153020","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.1.2595.6884"},{"key":"bibr17-02783649231153020","first-page":"1097","volume":"25","author":"Krizhevsky A","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr18-02783649231153020","doi-asserted-by":"publisher","DOI":"10.3390\/sym13020207"},{"key":"bibr19-02783649231153020","unstructured":"NASA (2003) Near. Mid and Far Infrared URL http:\/\/www.icc.dur.ac.uk\/tt\/Lectures\/Galaxies\/Images\/Infrared\/Regions\/irregions.html"},{"key":"bibr20-02783649231153020","doi-asserted-by":"crossref","unstructured":"Nirgudkar S, DeFilippo M, Sacarny M, et al. (2022) MassMIND: Massachusetts Maritime INfrared Dataset URL https:\/\/github.com\/uml-marine-robotics\/MassMIND","DOI":"10.1177\/02783649231153020"},{"key":"bibr21-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659477"},{"key":"bibr22-02783649231153020","volume-title":"Robotic Perception and Mapping: Emerging Techniques, ICRA Workshop","author":"Nirgudkar S","year":"2022"},{"key":"bibr23-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.157"},{"key":"bibr24-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2634580"},{"key":"bibr25-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116483"},{"key":"bibr26-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2775524"},{"key":"bibr27-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSE.2019.8867468"},{"key":"bibr28-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSKOBE.2018.8559310"},{"key":"bibr29-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"bibr30-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSKOBE.2018.8559310"},{"key":"bibr31-02783649231153020","unstructured":"SeaGrant (2022) MIT Sea Grant Marine Perception Dataset URL https:\/\/seagrant.mit.edu\/auvlab-datasets-marine-perception-1"},{"key":"bibr6-02783649231153020","unstructured":"Staples G (2020) Rosbag package URL http:\/\/wiki.ros.org\/rosbag"},{"key":"bibr32-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.103346"},{"key":"bibr33-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2017.03.009"},{"key":"bibr34-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301291"},{"key":"bibr35-02783649231153020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231153020","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649231153020","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231153020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:16:57Z","timestamp":1777457817000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649231153020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":34,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1177\/02783649231153020"],"URL":"https:\/\/doi.org\/10.1177\/02783649231153020","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}