Haoran Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haoran Liu has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Mingzhe Liu
College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China
12 shared publications - Peng Li
Chengdu University of Technology
11 shared publications - Zhuo Zuo
Chengdu University of Technology
9 shared publications Bing-Qi Liu
3 shared publications- Guibin Zan
Sigray, Inc., Concord, CA 94520, USA
3 shared publications - Kaimin Wang
Chengdu University of Technology
3 shared publications
Latest Publications
- 24 February 2026
- Published by Elsevier in Radiation Measurements
- Vol. 193
Pulse shape discrimination algorithms: Survey and benchmark
- 24 February 2026
- Published by Elsevier in Radiation Measurements
- Vol. 193
Pulse shape discrimination algorithms: Survey and benchmark
- 19 February 2026
- Published by Taylor & Francis in Nuclear Technology
- p. 1-13
Pulse Shape Discrimination of Neutrons and Gamma Rays Using Neuromorphic Models
- 19 February 2026
- Published by Taylor & Francis in Nuclear Technology
- p. 1-13
Pulse Shape Discrimination of Neutrons and Gamma Rays Using Neuromorphic Models
- Open Access
U-Net-Like Spiking Neural Networks for Single Image Dehazing
Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Transformers, have improved performance by effectively analyzing image features. However, CNNs struggle with long-range dependencies, and Transformers demand significant computational resources. To address these limitations, we propose DehazeSNN, an innovative architecture that integrates a U-Net-like design with Spiking Neural Networks (SNNs). DehazeSNN captures multi-scale image features while efficiently managing local and long-range dependencies. The introduction of the Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) enhances cross-channel communication, resulting in superior dehazing performance with reduced computational burden. Our extensive experiments show that DehazeSNN is highly competitive to state-of-the-art methods on benchmark datasets, delivering high-quality haze-free images with a smaller model size and less multiply-accumulate operations. The proposed dehazing method is publicly available at https://github.com/HaoranLiu507/DehazeSNN.
Open AccessU-Net-Like Spiking Neural Networks for Single Image Dehazing
Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Transformers, have improved performance by effectively analyzing image features. However, CNNs struggle with long-range dependencies, and Transformers demand significant computational resources. To address these limitations, we propose DehazeSNN, an innovative architecture that integrates a U-Net-like design with Spiking Neural Networks (SNNs). DehazeSNN captures multi-scale image features while efficiently managing local and long-range dependencies. The introduction of the Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) enhances cross-channel communication, resulting in superior dehazing performance with reduced computational burden. Our extensive experiments show that DehazeSNN is highly competitive to state-of-the-art methods on benchmark datasets, delivering high-quality haze-free images with a smaller model size and less multiply-accumulate operations. The proposed dehazing method is publicly available at https://github.com/HaoranLiu507/DehazeSNN.
- Open Access
- 28 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
RCNNshift: Moving Object Tracking with Kernel and Training-Free Spiking Neural Network
Moving object tracking is essential in computer vision applications such as autonomous navigation and surveillance. Traditional kernel-based methods like Meanshift and Camshift are computationally efficient but often falter with complex motions and occlusions. Deep learning approaches improve performance but require significant computational resources and extensive pretraining. In this paper, we present RCNNshift, a novel tracking algorithm that integrates Three-Dimensional Random-Coupled Neural Networks (3DRCNN) with the kernel-based window update process, eliminating the need for pretraining. RCNNshift constructs a robust feature space by leveraging spatiotemporal information from 3DRCNN, enabling effective tracking with reduced computational overhead. Additionally, it employs a one-dimensional feature space for the kernel-based window update step, which can improve efficiency compared to conventional multi-dimensional approaches. We evaluated RCNNshift on multiple datasets, where it consistently outperformed Meanshift and Camshift in accuracy and reliability, particularly in high-resolution and stable remote sensing environments. RCNNshift offers a promising balance between performance and computational efficiency, making it suitable for real-world applications where resources are limited.
- 28 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessRCNNshift: Moving Object Tracking with Kernel and Training-Free Spiking Neural Network
Moving object tracking is essential in computer vision applications such as autonomous navigation and surveillance. Traditional kernel-based methods like Meanshift and Camshift are computationally efficient but often falter with complex motions and occlusions. Deep learning approaches improve performance but require significant computational resources and extensive pretraining. In this paper, we present RCNNshift, a novel tracking algorithm that integrates Three-Dimensional Random-Coupled Neural Networks (3DRCNN) with the kernel-based window update process, eliminating the need for pretraining. RCNNshift constructs a robust feature space by leveraging spatiotemporal information from 3DRCNN, enabling effective tracking with reduced computational overhead. Additionally, it employs a one-dimensional feature space for the kernel-based window update step, which can improve efficiency compared to conventional multi-dimensional approaches. We evaluated RCNNshift on multiple datasets, where it consistently outperformed Meanshift and Camshift in accuracy and reliability, particularly in high-resolution and stable remote sensing environments. RCNNshift offers a promising balance between performance and computational efficiency, making it suitable for real-world applications where resources are limited.
- 26 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19  (10) , 1-9
Super-Resolution Image Reconstruction based on Random-coupled Neural Network and EDSR
- 26 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19  (10) , 1-9
Super-Resolution Image Reconstruction based on Random-coupled Neural Network and EDSR
- Open Access
- 6 January 2025
- Published by MDPI AG in Electronics
- Vol. 14  (1) , 210
Feature-Level Image Fusion Scheme for X-Ray Multi-Contrast Imaging
Since the mid-1990s, X-ray phase contrast imaging (XPCI) has attracted increasing interest in the industrial and bioimaging fields due to its high sensitivity to weakly absorbing materials and has gained widespread acceptance. XPCI can simultaneously provide three imaging modalities with complementary information, offering enriched details and data. This study proposes an image fusion method that simultaneously retrieves the three complementary channels of XPCI. It integrates block features, non-subsampled contourlet transform (NSCT), and a spiking cortical model (SCM), comprising three steps: (I) Image denoising, (II) Block-based feature-level NSCT-SCM fusion, and (III) Image quality enhancement. Compared with other methods in the XPCI image fusion field, the fusion results of the proposed algorithm demonstrated significant advantages, particularly with an impressive increase in the standard deviation by over 50% compared to traditional NSCT-SCM. The results revealed that the proposed algorithm exhibits high contrast, clear contours, and a short operation time. Experimental outcomes also demonstrated that the block-based feature extraction procedure performs better in retaining edge strength and texture information, with released computational resource consumption, thus, offering new possibilities for the industrial application of XPCI technology.
- 6 January 2025
- Published by MDPI AG in Electronics
- Vol. 14  (1) , 210
Open AccessFeature-Level Image Fusion Scheme for X-Ray Multi-Contrast Imaging
Since the mid-1990s, X-ray phase contrast imaging (XPCI) has attracted increasing interest in the industrial and bioimaging fields due to its high sensitivity to weakly absorbing materials and has gained widespread acceptance. XPCI can simultaneously provide three imaging modalities with complementary information, offering enriched details and data. This study proposes an image fusion method that simultaneously retrieves the three complementary channels of XPCI. It integrates block features, non-subsampled contourlet transform (NSCT), and a spiking cortical model (SCM), comprising three steps: (I) Image denoising, (II) Block-based feature-level NSCT-SCM fusion, and (III) Image quality enhancement. Compared with other methods in the XPCI image fusion field, the fusion results of the proposed algorithm demonstrated significant advantages, particularly with an impressive increase in the standard deviation by over 50% compared to traditional NSCT-SCM. The results revealed that the proposed algorithm exhibits high contrast, clear contours, and a short operation time. Experimental outcomes also demonstrated that the block-based feature extraction procedure performs better in retaining edge strength and texture information, with released computational resource consumption, thus, offering new possibilities for the industrial application of XPCI technology.
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Moving Object Tracking based on Kernel and Random-coupled Neural Network
Moving object tracking on cost-effective hardware is a crucial need in numerous research and industrial applications. However, current deep learning-based tracking algorithms usually prioritize exceptional performance at the expense of increased computational load. Due to the unavailability of expensive GPUs for many tracking tasks, these popular trackers often fall short in providing robust tracking capabilities with affordable computational resources. This study introduces RCNNshift, a kernel-based tracker that relies on feature extraction from a random-coupled neural network. This visual cortex inspired neural model can extract image features without requiring cumbersome pre-training or deep neural connections. By utilizing an enhanced one-dimensional feature representation, RCNNshift demonstrates superior performance compared to other kernel-based object tracking methods, even those employing higher-dimensional feature spaces. Its improvement in precision and success plots of OPE, compared to the Meanshift and Camshift in the HSV and RGB color spaces, exceeds over 160% and 190% respectively. Comparative experiments have validated the robustness of RCNNshift, showcasing its superior performance over various kernel-based and particle filter trackers. Its combination of robustness and computational efficiency makes RCNNshift an ideal choice for mid to low-end object tracking tasks such as surveillance and underwater tracking. The source code is available at https://github.com/HaoranLiu507/RCNNshift.
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessMoving Object Tracking based on Kernel and Random-coupled Neural Network
Moving object tracking on cost-effective hardware is a crucial need in numerous research and industrial applications. However, current deep learning-based tracking algorithms usually prioritize exceptional performance at the expense of increased computational load. Due to the unavailability of expensive GPUs for many tracking tasks, these popular trackers often fall short in providing robust tracking capabilities with affordable computational resources. This study introduces RCNNshift, a kernel-based tracker that relies on feature extraction from a random-coupled neural network. This visual cortex inspired neural model can extract image features without requiring cumbersome pre-training or deep neural connections. By utilizing an enhanced one-dimensional feature representation, RCNNshift demonstrates superior performance compared to other kernel-based object tracking methods, even those employing higher-dimensional feature spaces. Its improvement in precision and success plots of OPE, compared to the Meanshift and Camshift in the HSV and RGB color spaces, exceeds over 160% and 190% respectively. Comparative experiments have validated the robustness of RCNNshift, showcasing its superior performance over various kernel-based and particle filter trackers. Its combination of robustness and computational efficiency makes RCNNshift an ideal choice for mid to low-end object tracking tasks such as surveillance and underwater tracking. The source code is available at https://github.com/HaoranLiu507/RCNNshift.
- Open Access
- 31 October 2024
- Published by MDPI AG in Electronics
- Vol. 13  (21) , 4297
Random-Coupled Neural Network
Improving the efficiency of current neural networks and modeling them on biological neural systems have become prominent research directions in recent years. The pulse-coupled neural network (PCNN) is widely used to mimic the computational characteristics of the human brain in computer vision and neural network fields. However, PCNN faces limitations such as limited neural connections, high computational costs, and a lack of stochastic properties. This study proposes a random-coupled neural network (RCNN) to address these limitations. RCNN employs a stochastic inactivation process, selectively inactivating neural connections using a random inactivation weight matrix. This method reduces the computational burden and allows for extensive neural connections. RCNN encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, reflecting the information encoding characteristics of biological neural systems. Our experiments applied RCNN to image segmentation and fusion tasks, demonstrating its robustness, efficiency, and high noise resistance. Results indicate that RCNN surpasses traditional methods in performance across these applications.
- 31 October 2024
- Published by MDPI AG in Electronics
- Vol. 13  (21) , 4297
Open AccessRandom-Coupled Neural Network
Improving the efficiency of current neural networks and modeling them on biological neural systems have become prominent research directions in recent years. The pulse-coupled neural network (PCNN) is widely used to mimic the computational characteristics of the human brain in computer vision and neural network fields. However, PCNN faces limitations such as limited neural connections, high computational costs, and a lack of stochastic properties. This study proposes a random-coupled neural network (RCNN) to address these limitations. RCNN employs a stochastic inactivation process, selectively inactivating neural connections using a random inactivation weight matrix. This method reduces the computational burden and allows for extensive neural connections. RCNN encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, reflecting the information encoding characteristics of biological neural systems. Our experiments applied RCNN to image segmentation and fusion tasks, demonstrating its robustness, efficiency, and high noise resistance. Results indicate that RCNN surpasses traditional methods in performance across these applications.
- 16 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 71  (10) , 2297-2308
Pulse Shape Discrimination Based on the Tempotron: A Powerful Classifier on GPU
This study utilized the Tempotron, a robust classifier based on a third-generation neural network model, for pulse shape discrimination. By eliminating the need for manual feature extraction, the Tempotron model can process pulse signals directly, generating discrimination results based on prior knowledge. The study performed experiments using GPU acceleration, resulting in over 500 times faster compared to the CPU-based model, and investigated the impact of noise augmentation on the Tempotron performance. Experimental results substantiated that Tempotron serves as a formidable classifier, adept at accomplishing high discrimination accuracy on both AmBe and time-of-flight PuBe datasets. Furthermore, analyzing the neural activity of Tempotron during training shed light on its learning characteristics and aided in selecting its hyperparameters. Moreover, the study addressed the constraints and potential avenues for future development in utilizing the Tempotron for pulse shape discrimination. The dataset used in this study and the GPU-based Tempotron are publicly available on GitHub at https://github.com/HaoranLiu507/TempotronGPU.
- 16 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 71  (10) , 2297-2308
Pulse Shape Discrimination Based on the Tempotron: A Powerful Classifier on GPU
This study utilized the Tempotron, a robust classifier based on a third-generation neural network model, for pulse shape discrimination. By eliminating the need for manual feature extraction, the Tempotron model can process pulse signals directly, generating discrimination results based on prior knowledge. The study performed experiments using GPU acceleration, resulting in over 500 times faster compared to the CPU-based model, and investigated the impact of noise augmentation on the Tempotron performance. Experimental results substantiated that Tempotron serves as a formidable classifier, adept at accomplishing high discrimination accuracy on both AmBe and time-of-flight PuBe datasets. Furthermore, analyzing the neural activity of Tempotron during training shed light on its learning characteristics and aided in selecting its hyperparameters. Moreover, the study addressed the constraints and potential avenues for future development in utilizing the Tempotron for pulse shape discrimination. The dataset used in this study and the GPU-based Tempotron are publicly available on GitHub at https://github.com/HaoranLiu507/TempotronGPU.
- Open Access
Random-coupled Neural Network
Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the computation characteristics of the human brain in computer vision and neural network fields. However, differences between the PCNN and biological neural systems remain: limited neural connection, high computational cost, and lack of stochastic property. In this study, random-coupled neural network (RCNN) is proposed. It overcomes these difficulties in PCNN's neuromorphic computing via a random inactivation process. This process randomly closes some neural connections in the RCNN model, realized by the random inactivation weight matrix of link input. This releases the computational burden of PCNN, making it affordable to achieve vast neural connections. Furthermore, the image and video processing mechanisms of RCNN are researched. It encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, the same as biological neural information encoding characteristics. Finally, the RCNN is applicated to image segmentation, fusion, and pulse shape discrimination subtasks. It is demonstrated to be robust, efficient, and highly anti-noised, with outstanding performance in all applications mentioned above.
Open AccessRandom-coupled Neural Network
Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the computation characteristics of the human brain in computer vision and neural network fields. However, differences between the PCNN and biological neural systems remain: limited neural connection, high computational cost, and lack of stochastic property. In this study, random-coupled neural network (RCNN) is proposed. It overcomes these difficulties in PCNN's neuromorphic computing via a random inactivation process. This process randomly closes some neural connections in the RCNN model, realized by the random inactivation weight matrix of link input. This releases the computational burden of PCNN, making it affordable to achieve vast neural connections. Furthermore, the image and video processing mechanisms of RCNN are researched. It encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, the same as biological neural information encoding characteristics. Finally, the RCNN is applicated to image segmentation, fusion, and pulse shape discrimination subtasks. It is demonstrated to be robust, efficient, and highly anti-noised, with outstanding performance in all applications mentioned above.