Name
Abstract | ||
|---|---|---|
Indoor posture recognition is vital for monitoring/detecting exercises, activities of daily living, accidental falls, unusual behavior, etc. However, high -resolution image based systems have a high accuracy, they are considered as intrusive and most of the current state-of-the-art image classifiers (VGG, ImageNet, ResNext) are not applicable for ultra -low resolution (<32 pixels in extent) image classification due to their downsizing feature extraction architecture. Thus, we propose a shallow LowNet model for classifying privacy preserved 16x16 posture images with its feature preserving architecture, variable ReLU slopes, and a custom loss function. LowNet outperformed, with an Accuracy of 98.94% and F 1 -score of 79.86%, the existing models (LeNet, ResNet1, ResNet-2) which can run on our Ultra low- resolution Thermal Posture Image (UTPI38) dataset (offered here) with 38 classes (4374 samples) collected from 23 volunteers. More experimental results are discussed on the custom loss, and variable ReLU slopes which gave 8.2% performance increase. Thus, we conclude that LowNet is useful in a multi class ultra-low -resolution thermal posture image classification task. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICIP40778.2020.9190922 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Ultra -low resolution, CNN, thermal image, posture classification, privacy preserving | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Munkhjargal Gochoo | 1 | 14 | 4.41 |
| Tan-Hsu Tan | 2 | 21 | 10.28 |
| Fady Alnajjar | 3 | 66 | 12.23 |
| Jun-Wei Hsieh | 4 | 751 | 67.88 |
| Ping-Yang Chen | 5 | 2 | 4.12 |