MassMIND: Massachusetts Maritime INfrared Dataset
نویسندگان
چکیده
Recent advances in deep learning technology have triggered radical progress 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 sea transportation activities additional opportunities. These two use cases present very different terrains—the first being waters—with many obstacles, structures, human presence while latter is mostly devoid such obstacles. Variations environmental conditions common to both terrains. Robust labeled datasets mapping terrains crucial improving situational awareness drive However, there only limited maritime available these primarily consist optical images. Although, long wave infrared (LWIR) a strong complement spectrum helps extreme light conditions, public dataset with LWIR images does not currently exist. In paper, we fill gap by presenting over 2900 segmented captured environment period 2 years. The using instance segmentation classified into seven categories—sky, water, obstacle, living bridge, self, background. We also evaluate across three architectures (UNet, PSPNet, DeepLabv3) provide detailed analysis its efficacy. While focuses on terrain, it equally help cases. Such terrain would less traffic, classifier trained cluttered be able handle sparse scenes effectively. share research community hope spurs new scene understanding capabilities environment.
منابع مشابه
A Dataset for Airborne Maritime Surveillance Environments
This work presents a dataset with surveillance imagery over the sea captured by a small size UAV. This dataset presents object examples ranging from cargo ships, small boats, life rafts to hydrocarbon slick. The video sequences were captured using different types of cameras, at different heights and different perspectives. The dataset also contains thousands of labels with positions of objects ...
متن کاملA Panoramic Shortwave Infrared Hyperspectral Sensor for Maritime Sensing
Introduction: The U.S. Navy is exploring new technologies aimed at improving maritime electro-optic and infrared imaging systems. Specific goals include the enhancement of day/night, wide-area situational awareness; improved detection, identification, and tracking capabilities; and increased system reliability. Developing an imaging system that can accomplish these objectives is a tremendous de...
متن کاملImage Saliency Applied to Infrared Images for Unmanned Maritime Monitoring
This paper presents a method to detect boats and life rafts on long wave infrared (LWIR) images, captured by an aerial platform. The method applies the concept of image saliency to highlight distinct areas on the images. However saliency algorithms always highlight salient points in the image, even in the absence of targets. We propose a statistical method based on the saliency algorithm output...
متن کاملDataset of near infrared spectroscopy measurements to predict rheological parameters of sludge
In the dataset presented in this article, 36 sludge samples were characterized. Rheological parameters were determined and near infrared spectroscopy measurements were realized. In order to assess the potential of near infrared spectroscopy to predict rheological parameters of sludge, Partial Least Square algorithm was used to build calibration models.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The International Journal of Robotics Research
سال: 2023
ISSN: ['1741-3176', '0278-3649']
DOI: https://doi.org/10.1177/02783649231153020