A Novel Capability of Object Identification and Recognition Based on Integrated mWMM
Source abstract
Abstract
In the last decade, there has been remarkable progress in the areas of object detection and recognition due to high-quality color images along with their depth maps provided by RGB-D cameras. They enable artificially intelligent machines to easily detect and recognize objects and make real-time decisions according to the given scenarios. Depth cues can improve the quality of object detection and recognition. The main purpose of this research study to find an optimized way of object detection and identification we propose techniques of object detection using two RGB-D datasets. The proposed methodology extracts image normally from depth maps and then performs clustering using the Modified Watson Mixture Model (mWMM). mWMM is challenging to handle when the quality of the image is not good. Hence, the proposed RGB-D-based system uses depth cues for segmentation with the help of mWMM. Then it extracts multiple features from the segmented images. The selected features are fed to the Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) for detecting objects. We achieved 92.13% of mean accuracy over NYUv1 dataset and 90.00% of mean accuracy for the Redweb_v1 dataset. Finally, their results are compared and the proposed model with CNN outperforms other state-of-the-art methods. The proposed architecture can be used in autonomous cars, traffic monitoring, and sports scenes.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. LabelMe: A database and web-based tool for image annotation10.1007/s11263-007-0090-8 ↗
2. Indoor segmentation and support inference from rgbd images
3. Image classification based on segmentation-free object recognition
4. Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities
5. Learning rich features from rgb-d images for object detection and segmentation
6. 3dmatch: Learning local geometric descriptors from rgb-d reconstructions
7. Exactly robust kernel principal component analysis10.1109/TNNLS.2019.2909686 ↗
8. RGB-D images for objects recognition using 3D point clouds and RANSAC plane fitting
9. One-shot learning of object categories10.1109/TPAMI.2006.79 ↗
10. Locality-sensitive deconvolution networks with gated fusion for rgb-d indoor semantic segmentation
11. Learning hierarchical features for scene labeling10.1109/TPAMI.2012.231 ↗
12. Pose estimation and detection for event recognition using sense-aware features and adaboost classifier
13. Syntactic model-based human body 3D reconstruction and event classification via association based features mining and deep learning10.7717/peerj-cs.764 ↗
14. I. Akhter, “Automated posture analysis of gait event detection aia a hierarchical optimization algorithm and pseudo 2D stick-model,” M.S. Thesis, Dept. Computer science, Air University, Islamabad, Pakistan, 2020.
15. Scale invariant feature transform flow trajectory approach with applications to human action recognition
16. Convolutional-recursive deep learning for 3d object classification
17. Semi-supervised learning and feature evaluation for rgb-d object recognition10.1016/j.cviu.2015.05.007 ↗
18. Deep convolutional neural network-based fusion of RGB and IR images in marine environment
19. A unified multi-scale deep convolutional neural network for fast object detection
20. Deep convolutional neural network-based fusion of rgb and ir images in marine environment
21. Structured attention guided convolutional neural fields for monocular depth estimation
22. Rgb-d object recog-nition and pose estimation based on pre-trained convolutional neural network features
23. Histograms of oriented gradients for human detection
24. Distinctive image features from scale-invariant key-points10.1023/B:VISI.0000029664.99615.94 ↗
25. Region-based convolutional networks for accurate object detection and segmentation10.1109/TPAMI.2015.2437384 ↗
26. Faster r-cnn: Towards real-time object detection with region proposal networks
27. Ssd: Single shot multibox detector
28. You only look once: Unified, real-time object detection
29. Fast r-cnn
30. R-Fcn: Object detection via region-based fully convolutional networks
31. Demon: Depth and motion network for learning monocular stereo
32. Monocular depth estimation with hierarchical fusion of dilated cnns and soft-weighted-sum inference10.1016/j.patcog.2018.05.029 ↗
33. Df-net: Unsupervised joint learning of depth and flow using cross-task consistency
34. Digging into self-supervised monocular depth estimation
35. Unsupervised learning of depth and ego-motion from video
36. Cascaded feature network for semantic segmentation of rgb-d images
37. A spatiotemporal motion variation features extraction approach for human tracking and pose-based action recognition
38. Multiple events detection using context-intelligence features10.32604/iasc.2022.025013 ↗
39. Adaptive pose estimation for gait event detection using context-aware model and hierarchical optimization
40. Markerless sensors for physical health monitoring system using ecg and gmm feature extraction
41. Depth map-based human activity tracking and recognition using body joints features and self-organized map
42. Ridge body parts features for human pose estimation and recognition from RGB-D video data