Results 31 to 40 of about 9,227 (304)
Plant Phenomics, 2023 Although deep learning-based fruit detection techniques are becoming popular, they require a large number of labeled datasets to support model training. Moreover, the manual labeling process is time-consuming and labor-intensive.
Wenli Zhang +4 more
doaj +1 more source
An Unsupervised Deep Learning System for Acoustic Scene Analysis
Applied Sciences, 2020 Acoustic scene analysis has attracted a lot of attention recently. Existing methods are mostly supervised, which requires well-predefined acoustic scene categories and accurate labels. In practice, there exists a large amount of unlabeled audio data, but
Mou Wang +2 more
doaj +1 more source
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020 Remote sensing image scene classification, which aims at labeling remote sensing images with a set of semantic categories based on their contents, has broad applications in a range of fields.
Gong Cheng +4 more
doaj +1 more source
FUSION OF FEATURE BASED AND DEEP LEARNING METHODS FOR CLASSIFICATION OF MMS POINT CLOUDS [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019 This work proposes an approach for semantic classification of an outdoor-scene point cloud acquired with a high precision Mobile Mapping System (MMS), with major goal to contribute to the automatic creation of High Definition (HD) Maps.
D. Tosic +4 more
doaj +1 more source
Multicriteria-Based Active Discriminative Dictionary Learning for Scene Recognition
IEEE Access, 2018 Scene recognition is a significant and challenging problem in the field of computer vision. One of the principal bottlenecks in applying machine learning techniques to scene recognition tasks is the requirement of a large number of labeled training data.
Caixia Zheng +6 more
doaj +1 more source
Helping the Visually Impaired See via Image Multi-labeling Based on SqueezeNet CNN
Applied Sciences, 2019 This work presents a deep learning method for scene description. (1) Background: This method is part of a larger system, called BlindSys, that assists the visually impaired in an indoor environment.
Haikel Alhichri +3 more
doaj +1 more source
SCP: SCENE COMPLETION PRE-TRAINING FOR 3D OBJECT DETECTION [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023 3D object detection using LiDAR point clouds is a fundamental task in the fields of computer vision, robotics, and autonomous driving. However, existing 3D detectors heavily rely on annotated datasets, which are both time-consuming and prone to errors ...
Y. Shan +5 more
doaj +1 more source
Scene Labeling with Contextual Hierarchical Models
CoRR, 2014 Scene labeling is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in scene labeling frameworks has been widely realized in the field.
Mojtaba Seyedhosseini, Tolga Tasdizen
openaire +2 more sources
Label Tree Embeddings for Acoustic Scene Classification [PDF]
Proceedings of the 24th ACM international conference on Multimedia, 2016 We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering of the labels into multiple meta-classes in a tree structure.
Huy Phan +4 more
openaire +2 more sources
Using Scene Similarity for Place Labelling
, 2008 This paper is about labelling regions of a mobile robot’s workspace using scene appearance similarity. We do this by operating on a single matrix which expresses the pairwise similarity between all captured scenes. We describe and motivate a sequence of algorithms which, in conjunction with spatial constraints provided by the continuous motion of the ...
Posner, I, Schroeter, D, Newman, P
openaire +2 more sources