Motion perception is a fundamental function of biological visual systems, enabling organisms to navigate dynamic environments, detect threats, and track moving objects. Inspired by the mechanisms of biological motion processing, we propose an Unsupervised Artificial Visual System for motion direction detection. Unlike traditional supervised learning approaches, our model employs unsupervised learning to classify local motion direction detection neurons and group those with similar directional preferences to form macroscopic motion direction detection neurons. The activation of these neurons is proportional to the received input, and the neuron with the highest activation determines the macroscopic motion direction of the object. The proposed system consists of two layers: a local motion direction detection layer and an unsupervised global motion direction detection layer. For local motion detection, we adopt the Local Motion Detection Neuron (LMDN) model proposed in our previous work, which detects motion in eight different directions. The outputs of these neurons serve as inputs to the global motion direction detection layer, which employs a Gaussian Mixture Model (GMM) for unsupervised clustering. GMM, a probabilistic clustering method, effectively classifies local motion detection neurons according to their preferred directions, aligning with biological principles of sensory adaptation and probabilistic neural processing. Through repeated exposure to motion stimuli, our model self-organizes to detect macroscopic motion direction without the need for labeled data. Experimental results demonstrate that the GMM-based global motion detection layer successfully classifies motion direction signals, forming structured motion representations akin to biological visual systems. Furthermore, the system achieves motion direction detection accuracy comparable to previous supervised models while offering a more biologically plausible mechanism. This work highlights the potential of unsupervised learning in artificial vision and contributes to the development of adaptive motion perception models inspired by neural computation.

In recent research, dendritic neuron-based models have shown promise in effectively learning and recognizing object motion direction within binary images. Leveraging the dendritic neuron structure and On–Off Response mechanism within the primary cortex, this approach has notably reduced learning time and costs compared to traditional neural networks. This paper advances the existing model by integrating bio-inspired components into a learnable dendritic neuron-based artificial visual system (AVS), specifically incorporating mechanisms from horizontal and bipolar cells. This enhancement enables the model to proficiently identify object motion directions in grayscale images, aligning its threshold with human-like perception. The enhanced model demonstrates superior efficiency in motion direction recognition, requiring less data (90% less than other deep models) and less time for training. Experimental findings highlight the model’s remarkable robustness, indicating significant potential for real-world applications. The integration of bio-inspired features not only enhances performance but also opens avenues for further exploration in neural network research. Notably, the application of this model to realistic object recognition yields convincing accuracy at nearly 100%, underscoring its practical utility.

Motion direction detection is an essential task for both computer vision and neuroscience. Inspired by the biological theory of the human visual system, we proposed a learnable horizontal-cell-based dendritic neuron model (HCdM) that captures motion direction with high efficiency while remaining highly robust. Unlike present deep learning models, which rely on extension of computation and extraction of global features, the HCdM mimics the localized processing of dendritic neurons, enabling efficient motion feature integration. Through synaptic learning that prunes unnecessary parts, our model maintains high accuracy in noised images, particularly against salt-and-pepper noise. Experimental results show that the HCdM reached over 99.5% test accuracy, maintained robust performance under 10% salt-and-pepper noise, and achieved cross-dataset generalization exceeding 80% in certain conditions. Comparisons with state-of-the-art (SOTA) models like vision transformers (ViTs) and convolutional neural networks (CNNs) demonstrate the HCdM’s robustness and efficiency. Additionally, in contrast to previous artificial visual systems (AVSs), our findings suggest that lateral geniculate nucleus (LGN) structures, though present in biological vision, may not be essential for motion direction detection. This insight provides a new direction for bio-inspired computational models. Future research will focus on hybridizing the HCdM with SOTA models that perform well on complex visual scenes to enhance its adaptability.

The visual system of sighted animals plays a critical role in providing information about the environment, including motion details necessary for survival. Over the past few years, numerous studies have explored the mechanism of motion direction detection in the visual system for binary images, including the Hassenstein–Reichardt model (HRC model) and the HRC-based artificial visual system (AVS). In this paper, we introduced a contrast-response system based on previous research on amacrine cells in the visual system of Drosophila and other species. We combined this system with the HRC-based AVS to construct a motion-direction-detection system for gray-scale images. Our experiments verified the effectiveness of our model in detecting the motion direction in gray-scale images, achieving at least 99% accuracy in all experiments and a remarkable 100% accuracy in several circumstances. Furthermore, we developed two convolutional neural networks (CNNs) for comparison to demonstrate the practicality of our model.

This paper presents a biologically inspired model, the Stereoscopic Direction Detection Mechanism (SDDM), designed to detect motion direction in three-dimensional space. The model addresses two key challenges: the lack of biological interpretability in current deep learning models and the limited exploration of binocular functionality in existing biologically inspired models. Rooted in the fundamental concept of ’disparity’, the SDDM is structurally divided into components representing the left and right eyes. Each component mimics the layered architecture of the human visual system, from the retinal layer to the primary visual cortex. By replicating the functions of various cells involved in stereoscopic motion direction detection, the SDDM offers enhanced biological plausibility and interpretability. Extensive experiments were conducted to evaluate the model’s detection accuracy for various objects and its robustness against different types of noise. Additionally, to ascertain whether the SDDM matches the performance of established deep learning models in the field of three-dimensional motion direction detection, its performance was benchmarked against EfficientNet and ResNet under identical conditions. The results demonstrate that the SDDM not only exhibits strong performance and robust biological interpretability but also requires significantly lower hardware and time costs compared to advanced deep learning models.