Zhou Daniel Hao
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
Zhou Daniel Hao has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jigen Peng
School of Mathematics and Information Science, Guangzhou University, Guangzhou 510006, China
2 shared publications - Mingshuo Xu
School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
2 shared publications - Shigang Yue
School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
2 shared publications Abdulqader Dhafer
1 shared publicationHanxin Zhang
1 shared publication- Hao Luan
School of Automation and Electrical Engineering, Tianjin University of Technology and Education, Tianjin 300222, China
1 shared publication
Latest Publications
- Open Access
- 1 November 2026
- Published by MDPI AG in Biomimetics
- Vol. 11 (11) , 787
Beyond the Optic Lobe: Closing the Representational and Verification Gaps of STMD for Moving Target Proposal
Bio-inspired small-target motion detectors (STMDs) provide pixel-level saliency but lack proposal geometry and moving-target verification. Inspired by insect visual pathways, we present Beyond the Optic Lobe (BotL), a moving-target proposal framework compatible with seven STMD front-ends. A learning-free ON/OFF-histogram bridge converts saliency into boxes, and a binary verifier scores moving targets versus clutter without predicting categories. Under strict matching, BotL raises the area under the Recall versus false positives per image (FPPI) curve (AUC) for the default vSTMD-F front-end from 0.607 to 0.836 on re-annotated RIST and from 0.109 to 0.611 on SeaDronesSee-Tiny-SAHI (STS). Strict AUC and candidate Recall at a 15-proposal budget improve on every RIST test sequence. STS gains are large for the vSTMD family, moderate for FracSTMD, small for HaarSTMD, and negligible for ESTMD, DSTMD, and STMD+. Stage analysis distinguishes coverage constraints from verifier ranking limitations. YOLO detectors are more accurate in in-domain comparisons, but BotL leads in STS-to-RIST zero-shot transfer, with AUC 0.252 versus 0.016 and 0.030. BotL uses 16,341 learned parameters and reduces floating-point operations by a factor of 21–41 relative to these two YOLO detectors, serving as a compute-efficient proposal stage.
- 1 November 2026
- Published by MDPI AG in Biomimetics
- Vol. 11 (11) , 787
Open AccessBeyond the Optic Lobe: Closing the Representational and Verification Gaps of STMD for Moving Target Proposal
Bio-inspired small-target motion detectors (STMDs) provide pixel-level saliency but lack proposal geometry and moving-target verification. Inspired by insect visual pathways, we present Beyond the Optic Lobe (BotL), a moving-target proposal framework compatible with seven STMD front-ends. A learning-free ON/OFF-histogram bridge converts saliency into boxes, and a binary verifier scores moving targets versus clutter without predicting categories. Under strict matching, BotL raises the area under the Recall versus false positives per image (FPPI) curve (AUC) for the default vSTMD-F front-end from 0.607 to 0.836 on re-annotated RIST and from 0.109 to 0.611 on SeaDronesSee-Tiny-SAHI (STS). Strict AUC and candidate Recall at a 15-proposal budget improve on every RIST test sequence. STS gains are large for the vSTMD family, moderate for FracSTMD, small for HaarSTMD, and negligible for ESTMD, DSTMD, and STMD+. Stage analysis distinguishes coverage constraints from verifier ranking limitations. YOLO detectors are more accurate in in-domain comparisons, but BotL leads in STS-to-RIST zero-shot transfer, with AUC 0.252 versus 0.016 and 0.030. BotL uses 16,341 learned parameters and reduces floating-point operations by a factor of 21–41 relative to these two YOLO detectors, serving as a compute-efficient proposal stage.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1
vSTMD: Visual Motion Detection for Extremely Tiny Target at Various Velocities
Visual motion detection for extremely tiny (ET-) targets is challenging, due to their category-independent nature and the scarcity of visual cues, which often incapacitate mainstream feature-based models. Natural architectures with rich interpretability offer a promising alternative, where STMD architectures derived from insect visual STMD (Small Target Motion Detector) pathways have demonstrated their effectiveness. However, previous STMD models are constrained to a narrow velocity range, hindering their efficacy in real-world scenarios where targets exhibit diverse and unstable dynamics. To address this limitation, we present vSTMD, a learning-free model for motion detection of ET-targets at various velocities. vSTMD proposes two key mechanisms: cross-Inhibition Dynamic Potential (cIDP) and Collaborative Directional Gradient Calculation (CDGC). Specifically, cIDP serves as a self-adaptive mechanism, efficiently capturing motion cues across a wide velocity spectrum. CDGC enhances orienting accuracy and robustness while reducing computational overhead to one-eighth of previously isolated strategies. Evaluated on the real-world dataset RIST, the proposed vSTMD and its feedback-facilitated variant vSTMD-F achieve relative F1 gains of 30% and 58% over state-of-the-art STMD approaches, respectively. Furthermore, both models demonstrate competitive orientation estimation performance compared to SOTA deep learning-driven methods. Experiments also reveal the superiority of the natural architecture for ET-object motion detection - vSTMD is 60× faster than contemporary data-driven methods, making it highly suitable for real-time applications in dynamic scenarios and complex backgrounds. Code is available at Project Repository.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1
vSTMD: Visual Motion Detection for Extremely Tiny Target at Various Velocities
Visual motion detection for extremely tiny (ET-) targets is challenging, due to their category-independent nature and the scarcity of visual cues, which often incapacitate mainstream feature-based models. Natural architectures with rich interpretability offer a promising alternative, where STMD architectures derived from insect visual STMD (Small Target Motion Detector) pathways have demonstrated their effectiveness. However, previous STMD models are constrained to a narrow velocity range, hindering their efficacy in real-world scenarios where targets exhibit diverse and unstable dynamics. To address this limitation, we present vSTMD, a learning-free model for motion detection of ET-targets at various velocities. vSTMD proposes two key mechanisms: cross-Inhibition Dynamic Potential (cIDP) and Collaborative Directional Gradient Calculation (CDGC). Specifically, cIDP serves as a self-adaptive mechanism, efficiently capturing motion cues across a wide velocity spectrum. CDGC enhances orienting accuracy and robustness while reducing computational overhead to one-eighth of previously isolated strategies. Evaluated on the real-world dataset RIST, the proposed vSTMD and its feedback-facilitated variant vSTMD-F achieve relative F1 gains of 30% and 58% over state-of-the-art STMD approaches, respectively. Furthermore, both models demonstrate competitive orientation estimation performance compared to SOTA deep learning-driven methods. Experiments also reveal the superiority of the natural architecture for ET-object motion detection - vSTMD is 60× faster than contemporary data-driven methods, making it highly suitable for real-time applications in dynamic scenarios and complex backgrounds. Code is available at Project Repository.
- Open Access
- 16 June 2025
- Published by Springer Nature in Metallurgical and Materials Transactions B
- Vol. 56 (4) , 4201-4217
Deep Transformers for Analyzing BOF Steelmaking Data
This study investigates the application of advanced deep learning models, particularly transformer-based architectures, to model the basic oxygen furnace (BOF) steelmaking process, with a focus on accurately predicting endpoint temperature. Achieving precise temperature predictions is critical for optimizing process parameters, enhancing product quality, and ensuring energy efficiency in BOF operations. This research represents the first extensive deployment of such models on BOF operational data. We rigorously evaluated five state-of-the-art deep learning models using a comprehensive dataset consisting of over 10,000 samples from a large-scale industrial setting. Among these models, we introduced a novel architecture, TTB-BOFNet, tailored to handle the complexities of industrial-scale BOF data. TTB-BOFNet leverages transformer models enhanced through exploratory data analysis-informed binning to better interpret intricate interactions and generate contextual embeddings. Our novel architecture demonstrated a notable improvement in predictive performance, achieving an 8.81 pct improvement in R-squared over XGBoost, a 4.65 pct gain over the multi-layer perceptron (MLP) benchmark and a 1.79 pct improvement over the TabTransformer model. Additionally, SHapley Additive exPlanations (SHAP) analysis was employed to interpret the TTB-BOFNet model predictions, revealing the effectiveness of both the EDA-informed binning approach and the model’s transformer-based structure in capturing critical features and improving predictive accuracy. These findings underscore the potential of transformer-based deep learning models to optimize complex industrial operations. TTB-BOFNet offers a robust, interpretable, and scalable solution for BOF temperature prediction, paving the way for more adaptive, data-driven decision-making in steel manufacturing.
- 16 June 2025
- Published by Springer Nature in Metallurgical and Materials Transactions B
- Vol. 56 (4) , 4201-4217
Open AccessDeep Transformers for Analyzing BOF Steelmaking Data
This study investigates the application of advanced deep learning models, particularly transformer-based architectures, to model the basic oxygen furnace (BOF) steelmaking process, with a focus on accurately predicting endpoint temperature. Achieving precise temperature predictions is critical for optimizing process parameters, enhancing product quality, and ensuring energy efficiency in BOF operations. This research represents the first extensive deployment of such models on BOF operational data. We rigorously evaluated five state-of-the-art deep learning models using a comprehensive dataset consisting of over 10,000 samples from a large-scale industrial setting. Among these models, we introduced a novel architecture, TTB-BOFNet, tailored to handle the complexities of industrial-scale BOF data. TTB-BOFNet leverages transformer models enhanced through exploratory data analysis-informed binning to better interpret intricate interactions and generate contextual embeddings. Our novel architecture demonstrated a notable improvement in predictive performance, achieving an 8.81 pct improvement in R-squared over XGBoost, a 4.65 pct gain over the multi-layer perceptron (MLP) benchmark and a 1.79 pct improvement over the TabTransformer model. Additionally, SHapley Additive exPlanations (SHAP) analysis was employed to interpret the TTB-BOFNet model predictions, revealing the effectiveness of both the EDA-informed binning approach and the model’s transformer-based structure in capturing critical features and improving predictive accuracy. These findings underscore the potential of transformer-based deep learning models to optimize complex industrial operations. TTB-BOFNet offers a robust, interpretable, and scalable solution for BOF temperature prediction, paving the way for more adaptive, data-driven decision-making in steel manufacturing.
- Open Access
A Generative System for Robot-to-Human Handovers: from Intent Inference to Spatial Configuration Imagery
We propose a novel system for robot-to-human object handover that emulates human coworker interactions. Unlike most existing studies that focus primarily on grasping strategies and motion planning, our system focus on 1. inferring human handover intents, 2. imagining spatial handover configuration. The first one integrates multimodal perception-combining visual and verbal cues-to infer human intent. The second one using a diffusion-based model to generate the handover configuration, involving the spacial relationship among robot's gripper, the object, and the human hand, thereby mimicking the cognitive process of motor imagery. Experimental results demonstrate that our approach effectively interprets human cues and achieves fluent, human-like handovers, offering a promising solution for collaborative robotics. Code, videos, and data are available at: https://i3handover.github.io.
Open AccessA Generative System for Robot-to-Human Handovers: from Intent Inference to Spatial Configuration Imagery
We propose a novel system for robot-to-human object handover that emulates human coworker interactions. Unlike most existing studies that focus primarily on grasping strategies and motion planning, our system focus on 1. inferring human handover intents, 2. imagining spatial handover configuration. The first one integrates multimodal perception-combining visual and verbal cues-to infer human intent. The second one using a diffusion-based model to generate the handover configuration, involving the spacial relationship among robot's gripper, the object, and the human hand, thereby mimicking the cognitive process of motor imagery. Experimental results demonstrate that our approach effectively interprets human cues and achieves fluent, human-like handovers, offering a promising solution for collaborative robotics. Code, videos, and data are available at: https://i3handover.github.io.
- 9 June 2017
- Published by Springer Nature in CEAS Space Journal
- Vol. 10 (1) , 101-113
Using the attitude response of aerostable spacecraft to measure thermospheric wind
- 9 June 2017
- Published by Springer Nature in CEAS Space Journal
- Vol. 10 (1) , 101-113
Using the attitude response of aerostable spacecraft to measure thermospheric wind