Linhua Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Linhua Ye has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Ronghua Luo
South China University of Technology
4 shared publications - Yangyang Huang
College of Computer Science and Engineering, South China University of Technology, Guangdong, China
3 shared publications - Songhang Chen
Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou 350108, China
2 shared publications Yonghang Shen
Zhejiang Univ. (China)
2 shared publications- Limin Tong
New Cornerstone Science Laboratory, State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, China
1 shared publication Meng Guo
Fujian Normal University
1 shared publication
Latest Publications
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1596-1609
Robust Unknown Object Detection in Dynamic Environments Through Dual-Granularity Reconstruction Error Modeling
Open World Object Detection (OWOD) aims to detect both known and unknown objects in dynamic environments, where unknown instances lack ground-truth supervision during training. Existing methods typically rely on supervision from known categories, leading models to overconfidently classify visually similar unknowns as known classes, and dissimilar ones as background. This known-class prior bias severely hinders the detection of truly novel objects. To address this challenge, we propose a robust unknown object detection method based on dual-granularity reconstruction error modeling. At the fine-grained level, we propose Fine-grained Masked Reconstruction (FMR), which randomly masks feature regions to guide reconstruction toward semantic structures, thereby improving foreground–background discrimination. At the coarse-grained level, we propose Adaptive Region-based Error Aggregation (AREA), which aggregates reconstruction errors over object proposals to enhance the model’s sensitivity to ambiguous semantic boundaries while suppressing local outliers. Furthermore, we perform decoupled probabilistic modeling of foreground and background reconstruction errors, enabling soft estimation of unknown object likelihoods without supervision. Extensive experiments on standard OWOD benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving a +20.6 improvement in unknown object recall (U-Recall) while maintaining strong performance on known classes.
- 27 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1596-1609
Robust Unknown Object Detection in Dynamic Environments Through Dual-Granularity Reconstruction Error Modeling
Open World Object Detection (OWOD) aims to detect both known and unknown objects in dynamic environments, where unknown instances lack ground-truth supervision during training. Existing methods typically rely on supervision from known categories, leading models to overconfidently classify visually similar unknowns as known classes, and dissimilar ones as background. This known-class prior bias severely hinders the detection of truly novel objects. To address this challenge, we propose a robust unknown object detection method based on dual-granularity reconstruction error modeling. At the fine-grained level, we propose Fine-grained Masked Reconstruction (FMR), which randomly masks feature regions to guide reconstruction toward semantic structures, thereby improving foreground–background discrimination. At the coarse-grained level, we propose Adaptive Region-based Error Aggregation (AREA), which aggregates reconstruction errors over object proposals to enhance the model’s sensitivity to ambiguous semantic boundaries while suppressing local outliers. Furthermore, we perform decoupled probabilistic modeling of foreground and background reconstruction errors, enabling soft estimation of unknown object likelihoods without supervision. Extensive experiments on standard OWOD benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving a +20.6 improvement in unknown object recall (U-Recall) while maintaining strong performance on known classes.
- 13 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
SALLM: Open world object detection empowered by self adaptive learning and large model
- 13 August 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 297
SALLM: Open world object detection empowered by self adaptive learning and large model
- 24 July 2025
- Published by Springer Nature
- p. 63-73
Decoupled Modeling of Foreground and Background for Open-World Object Detection
- 24 July 2025
- Published by Springer Nature
- p. 63-73
Decoupled Modeling of Foreground and Background for Open-World Object Detection
- 28 December 2023
- Published by Springer Nature
- p. 340-351
A Real-Time Safety Detector Based on Re-parameterization Multiscale Feature Fusion for Forklift Driving
- 28 December 2023
- Published by Springer Nature
- p. 340-351
A Real-Time Safety Detector Based on Re-parameterization Multiscale Feature Fusion for Forklift Driving
- Open Access
- 1 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 86509-86521
GBForkDet: A Lightweight Object Detector for Forklift Safety Driving
The importance of object detection in intelligent logistics applications is increasingly recognized. However, current detector models suffer from challenges such as high computational cost and low detection accuracy, which limit their deployment on edge devices with limited computational power in logistics scenarios. To address these issues, this paper proposes a novel lightweight detector model (GBForkDet) based on YOLOv8 for forklift safety driving. Firstly, the Ghost module is integrated into YOLOv8 to optimize the Backbone feature extraction process, reducing the computational cost of the model. Then, a Bi-directional Omni-Dimensional Dynamic Neck (BiODNeck) is designed to fuse feature information in complex logistics scenarios. GBForkDet significantly improves the capture of contextual logistics background information by reconstructing the Neck of YOLOv8 with BiODNeck. This is attributed to cross-layer weighted feature fusion and a complementary focus on learning convolutional kernels in any convolutional layer along all four dimensions of the kernel space. Furthermore, the introduction of the Normalized Wasserstein distance (NWD) as an enhanced loss function improves the detection of small distant objects in logistics scenarios. Experimental results show that GBForkDet achieves a mAP of 92.7% and 95.3% on the established Forklift-3k and KITTI datasets while reducing the model parameters by 17.9% and the computational cost by 22.5% compared to the baseline YOLOv8s model. Under the Jetson Nano edge platform and 640×640 input size, the GBForkDet model achieves a remarkable inference time of 108.2 ms using TensorRT acceleration.
- 1 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 86509-86521
Open AccessGBForkDet: A Lightweight Object Detector for Forklift Safety Driving
The importance of object detection in intelligent logistics applications is increasingly recognized. However, current detector models suffer from challenges such as high computational cost and low detection accuracy, which limit their deployment on edge devices with limited computational power in logistics scenarios. To address these issues, this paper proposes a novel lightweight detector model (GBForkDet) based on YOLOv8 for forklift safety driving. Firstly, the Ghost module is integrated into YOLOv8 to optimize the Backbone feature extraction process, reducing the computational cost of the model. Then, a Bi-directional Omni-Dimensional Dynamic Neck (BiODNeck) is designed to fuse feature information in complex logistics scenarios. GBForkDet significantly improves the capture of contextual logistics background information by reconstructing the Neck of YOLOv8 with BiODNeck. This is attributed to cross-layer weighted feature fusion and a complementary focus on learning convolutional kernels in any convolutional layer along all four dimensions of the kernel space. Furthermore, the introduction of the Normalized Wasserstein distance (NWD) as an enhanced loss function improves the detection of small distant objects in logistics scenarios. Experimental results show that GBForkDet achieves a mAP of 92.7% and 95.3% on the established Forklift-3k and KITTI datasets while reducing the model parameters by 17.9% and the computational cost by 22.5% compared to the baseline YOLOv8s model. Under the Jetson Nano edge platform and 640×640 input size, the GBForkDet model achieves a remarkable inference time of 108.2 ms using TensorRT acceleration.
- 10 September 2002
- Published by SPIE-Intl Soc Optical Eng
- Vol. 4920, 25-31
Sapphire fiber thermometer based on fluorescence lifetime measurement
A sapphire fiber thermometer probe with Cr3+ ion doped tip end was grown from the laser heated pedestal growth method. The fiber probe offers advantages of compact construct, high performance and ability to withstand high temperature. The temperature dependence of fluorescence of the probe was investigated, and a sapphire fiber thermometer based on its fluorescent decay was presented. Among the detection rang from the room temperature to 450 c , the thermometer has an average temperature resolution of 10C.The thermometer may be used in microwave treatment and thermal monitoring of Medium Voltage substations.
- 10 September 2002
- Published by SPIE-Intl Soc Optical Eng
- Vol. 4920, 25-31
Sapphire fiber thermometer based on fluorescence lifetime measurement
A sapphire fiber thermometer probe with Cr3+ ion doped tip end was grown from the laser heated pedestal growth method. The fiber probe offers advantages of compact construct, high performance and ability to withstand high temperature. The temperature dependence of fluorescence of the probe was investigated, and a sapphire fiber thermometer based on its fluorescent decay was presented. Among the detection rang from the room temperature to 450 c , the thermometer has an average temperature resolution of 10C.The thermometer may be used in microwave treatment and thermal monitoring of Medium Voltage substations.
- 1 January 1999
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 10 (7) , 607-611
A zirconia single-crystal fibre-optic sensor for contact measurement of temperatures above 2000 °C
- 1 January 1999
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 10 (7) , 607-611
A zirconia single-crystal fibre-optic sensor for contact measurement of temperatures above 2000 °C