Results 141 to 150 of about 16,805 (257)

Improved Mask R-CNN Multi-Target Detection and Segmentation for Autonomous Driving in Complex Scenes. [PDF]

Sensors (Basel), 2023
Fang S, Zhang B, Hu J.
europepmc   +1 more source

Formation Control With Obstacle Avoidance of Underwater Swarms Based on Relative Visual Feedback

Journal of Field Robotics, EarlyView.
ABSTRACT Underwater multi‐robot and swarm systems require advanced methodologies for controlling collective behavior. Conventional single‐robot techniques, such as tethering, sonar imaging, and acoustic localization, are not scalable or effective for swarm applications.
Andrea Infanti, Saverio Iacoponi, Saif Alameri, Mohamed El Hanbaly, Mohammed Tarnini, Cesare Stefanini, Giulia De Masi, Federico Renda   +7 more
wiley   +1 more source

Time‐series digital camera photos combined with machine learning algorithms can realize accurate observation of flowering phenology

Remote Sensing in Ecology and Conservation, EarlyView.
Intelligent approaches are required to extract valuable phenological information from time‐series digital camera photos. In this research, we employed YOLO‐based object detection and semantic segmentation models to identify flowers and flower pixels, acquire flower count and flower cover data, and extract phenophases such as first, peak, and end ...
Chuangye Song, Yuan Jia, Lin Zhang, Dongxiu Wu   +3 more
wiley   +1 more source

Comparison of Mask-R-CNN and Thresholding-Based Segmentation for High-Throughput Phenotyping of Walnut Kernel Color. [PDF]

Plants (Basel)
Lee SH, McDowell S, Leslie C, McCreery K, Earles M, Brown PJ.   +5 more
europepmc   +1 more source

Simultaneous Segmentation and Classification of Pressure Injury Image Data Using Mask-R-CNN. [PDF]

Comput Math Methods Med, 2023
Swerdlow M, Guler O, Yaakov R, Armstrong DG.   +3 more
europepmc   +1 more source

Retrospective image analysis for long‐term demography using Google Earth imagery

Remote Sensing in Ecology and Conservation, EarlyView.
We demonstrate that high‐resolution Google Earth imagery, combined with minimal field validation, enables retrospective tracking of individual invasive plants. The image shows one of the monitored individuals of Opuntia sp. in Greece. Our approach reveals long‐term demographic patterns, recruitment dynamics, and spatial expansion without continuous ...
Erola Fenollosa, Garrett Cohen, Roberto Salguero‐Gómez   +2 more
wiley   +1 more source

Research on Instance Segmentation Algorithm for Caged Chickens in Infrared Images Based on Improved Mask R-CNN. [PDF]

Sensors (Basel)
Chen Y, Liu H, Wang L, Chen C, Li S, Zhong B, Qiao J, Ye R, Li T.   +8 more
europepmc   +1 more source

Segmentation of mine overburden dump particles from images using Mask R CNN. [PDF]

Sci Rep, 2023
Shrivastava S, Bhattacharjee S, Deb D.
europepmc   +1 more source

Few Annotations, High Accuracy: Transfer Learning and Data Augmentation Improve Passive Acoustic Monitoring of the Vulnerable African Manatee

Remote Sensing in Ecology and Conservation, EarlyView.
Can deep learning reliably detect a threatened species in passive acoustic monitoring with few annotations? Across 52 sites and 600 recording days, we compared two deep learning recognizers with the traditional machine learning Kaleidoscope for detecting African manatee vocalizations.
Lucas Dubus, Auguste Verdier, Nina Giotto, Grace Mbemba, Gabriel Michelin, Baptiste Mulot, Stéphanie Manel, David Mouillot   +7 more
wiley   +1 more source

Correction: Optimizing Mask R-CNN for enhanced quinoa panicle detection and segmentation in precision agriculture. [PDF]

Front Plant Sci
El Akrouchi M, Mhada M, Gracia DR, Hawkesford MJ, Gérard B.   +4 more
europepmc   +1 more source