Object Detection based on Mask R-CNN from Infrared Camera

Song, Hyun Chul; Knag, Min-Sik; Kimg, Tae-Eun

doi:10.9728/dcs.2018.19.6.1213

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They improved the performance of thermal infrared object detection tasks by adjusting the feature extractor. Song et al [ 4 ] created a segmentation template for the heat-generating part for the heat-generating components in the thermal-sensing image of a thermal infrared camera. They proposed a mask-based RCNN-based infrared image detection algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…To obtain better thermal infrared target detection performance and detection efficiency, the existing advanced thermal infrared target detectors are mainly two-stage RCNN framework and lightweight single-stage Yolo series [ 4 ], in which the two-stage RCNN [ 5 , 6 ] consists of a region proposal network (RPN) [ 7 ] Generate high-quality regions of interest from horizontal anchors for efficient features, and utilize bounding regression boxes for regression and classification. It is worth noting that the horizontal anchor point quickly leads to a severe imbalance between the bounding box and the directional target object.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LAGSwin: Local attention guided Swin-transformer for thermal infrared sports object detection

Meng,

Si,

Mao

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Compared with visible light images, thermal infrared images have poor resolution, low contrast, signal-to-noise ratio, blurred visual effects, and less information. Thermal infrared sports target detection methods relying on traditional convolutional networks capture the rich semantics in high-level features but blur the spatial details. The differences in physical information content and spatial distribution of high and low features are ignored, resulting in a mismatch between the region of interest and the target. To address these issues, we propose a local attention-guided Swin-transformer thermal infrared sports object detection method (LAGSwin) to encode sports objects’ spatial transformation and orientation information. On the one hand, Swin-transformer guided by local attention is adopted to enrich the semantic knowledge of low-level features by embedding local focus from high-level features and generating high-quality anchors while increasing the embedding of contextual information. On the other hand, an active rotation filter is employed to encode orientation information, resulting in orientation-sensitive and invariant features to reduce the inconsistency between classification and localization regression. A bidirectional criss-cross fusion strategy is adopted in the feature fusion stage to enable better interaction and embedding features of different resolutions. At last, the evaluation and verification of multiple open-source sports target datasets prove that the proposed LAGSwin detection framework has good robustness and generalization ability.

show abstract

Section: Related Workmentioning

confidence: 99%