Attention-Driven LPLC2 Neural Ensemble Model for Multi-Target Looming Detection and Localization

2025-04-06

AI Summary

Existing LPLC2 neuron models struggle to achieve global, real-time detection and precise localization of multiple approaching targets. This paper proposes a fruit-fly-inspired population-level LPLC2 neural model that innovatively couples motion-driven bottom-up attention with radial motion antagonism, overcoming the inherent limitation of single-target center detection. By jointly modeling dynamic attention fields and population-level nonlinear responses, the model enables concurrent discrimination and continuous tracking of multiple approaching objects across the entire visual field. Evaluated on both synthetic simulations and real-world UAV video data, the model achieves a response latency of <10 ms, multi-target detection accuracy >92%, and angular localization error <3.5°—significantly outperforming both single-cell LPLC2 models and conventional population-voting approaches.

Technology Category

• Computer Vision: Motion & Tracking
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Lobula plate/lobula columnar, type 2 (LPLC2) visual projection neurons in the fly's visual system possess highly looming-selective properties, making them ideal for developing artificial collision detection systems. The four dendritic branches of individual LPLC2 neurons, each tuned to specific directional motion, enhance the robustness of looming detection by utilizing radial motion opponency. Existing models of LPLC2 neurons either concentrate on individual cells to detect centroid-focused expansion or utilize population-voting strategies to obtain global collision information. However, their potential for addressing multi-target collision scenarios remains largely untapped. In this study, we propose a numerical model for LPLC2 populations, leveraging a bottom-up attention mechanism driven by motion-sensitive neural pathways to generate attention fields (AFs). This integration of AFs with highly nonlinear LPLC2 responses enables precise and continuous detection of multiple looming objects emanating from any region of the visual field. We began by conducting comparative experiments to evaluate the proposed model against two related models, highlighting its unique characteristics. Next, we tested its ability to detect multiple targets in dynamic natural scenarios. Finally, we validated the model using real-world video data collected by aerial robots. Experimental results demonstrate that the proposed model excels in detecting, distinguishing, and tracking multiple looming targets with remarkable speed and accuracy. This advanced ability to detect and localize looming objects, especially in complex and dynamic environments, holds great promise for overcoming collision-detection challenges in mobile intelligent machines.

Problem

• Detects multiple looming objects in visual fields
• Improves collision detection in dynamic environments
• Enhances accuracy and speed for mobile robots

Innovation

• Attention-driven LPLC2 neural ensemble model
• Motion-sensitive neural pathways generate attention fields
• Detects multiple looming targets with high accuracy