ABSTRACT Forests are crucial terrestrial ecosystems. To understand long‐term forest community evolution driven by multiple environmental factors, we constructed a 3D forest stand spatiotemporal evolution framework featuring synchronous bidirectional coupling between terrain, hydrology, radiation, and vegetation. First, we simulated topographical evolution using a physics‐based procedural erosion method and introduced a multi‐layer soil moisture model and individual tree growth response mechanisms to reflect‐topography interactions, thereby establishing a realistic environmental basis for forest stand evolution. Second, leveraging real environmental data, we simulated growth responses and biomass changes of forest stands under different precipitation and radiation conditions, elucidated response mechanisms of individual tree attributes to environmental changes, and achieved intuitive evolution of 3D forest stands. The framework advances beyond unidirectional environmental forcing models by integrating hydraulic erosion, soil moisture dynamics, and slope‐aware radiation within a unified monthly timestep, enabling co‐evolutionary simulation of forest stands under dynamic landscapes. Finally, the computer‐based model incorporated natural disaster events such as fires and droughts, with real‐time interaction and visualization capabilities, supporting immersive and responsive forest landscape simulation and detailed spatiotemporal evolution analysis, enabling assessment of the dynamic recovery processes of forest stands under multiple disturbance scenarios.

Garment is an essential component of digital humans, and the accurate representation of dynamic simulation details and wrinkle characteristics is crucial for enhancing the realism of virtual scenes. However, this task remains significantly challenging in complex simulation scenarios. Therefore, we propose a novel garment simulation method based on Graph Neural Networks (GNNs), referred to as SAGS-GNN, which effectively simulates self-collision and cloth anisotropy. To tackle the self-collision problem, we present the repulsive loss term and the maximum depth loss term. These terms effectively simulate the interactions between the vertices of the cloth mesh by jointly constraining their positions, thereby facilitating the self-collision handling of garments. Furthermore, our approach utilizes the Neo-Hookean StVK method to achieve anisotropy in cloth, further reflecting the different wrinkle details of multiple materials during motion. In summary, our SAGS method effectively mitigates the issue of interpenetration among garments, facilitates the realization of anisotropic properties in a variety of fabric materials, and significantly enhances the visual realism of virtual apparel. We evaluate our method on various garment types and materials, demonstrating competitive qualitative and quantitative results.

Group activity recognition (GAR) is a challenging task in computer vision, which needs to comprehensively model the spatiotemporal relations among actors. However, most previous methods tend to only model unitary actor relations and directly aggregate actor features to form group representation at a single scale. To address these issues, we propose a novel GAR approach termed multi-scale cross-distance transformer (MSCD-Former), capable of capturing diverse actor relation contexts in multiple spatiotemporal scales. A cross-distance attentive block (CDA-Block) is designed to decompose the actor relations into local and distant ones, diversifying the relation features in rearranged groups. The multi-scale group descriptors are then enhanced by deploying stacked CDA-Blocks to cascaded stages and tightening the sampling scales accordingly. Moreover, we introduce a multi-scale reconstructive learning measure (MSR-Learning) between adjacent scales of CDA-Blocks. Via the reconstruction of actor relational features from lower scales to upper scales, MSR-Learning can enforce semantic consistency in multiple spatiotemporal scales. Consequently, our MSCD-Former boosts GAR by fusing such discriminative relation features of different scales. We extensively evaluate the proposed approach on the VolleyTactic, Volleyball, Collective Activity, NBA, and JRDB-PAR datasets, and the experimental results demonstrate its superiority.

Flower plants have become a major difficulty in virtual plant research because of their rich external morphological structure and complex physiological processes. Computer vision simulation provides powerful tools for exploring powerful biological systems and operating laws. In this paper, Chrysanthemum and Chinese rose, double flowers as the symbolic flowers of Beijing, are chosen as the study subject. On the basis of maximizing the protection of flower growth structure, an effective method based on laser scanning for three-dimensional (3D) reconstruction and visual simulation of flower plants is proposed. This method uses laser technology to scan the sample and store it as point cloud data. After applying a series of image analysis and processing techniques such as splicing, denoising, repairing and color correction, the digital data optimized by the sample is obtained accurately and efficiently, and a highly realistic 3D simulation model of the plant is formed. The results of the research indicate that it is a convenient research method for the 3D reconstruction of flower plants and computer vision simulation of virtual plants. It also provides an effective way for in-depth study of scientific experiments and digital protection of rare and endangered plants.

As the recent novel somatosensory devices become more pervasive, dynamic hand gesture recognition algorithm has attracted substantial research attention and has been widely used in the area of human–computer interaction (HCI). This paper aims to develop low-complexity and real-time solutions of dynamic hand gesture recognition using Leap Motion Controller (LMC) for flower and plant interactive applications. In this paper, we use two LMCs to obtain gesture data from different angles for fusion processing and then propose a novel feature vector, which adapts to representing dynamic hand gestures. After this, an improved Hidden Markov Model (HMM) algorithm was proposed to obtain the final recognition results, in which we apply the Particle Swarm Optimization (PSO) to avoid the complex computation of parameters in conventional HMM, thus improving the recognition performance. The experimental results on test datasets demonstrate that the proposed algorithm can achieve a higher average recognition rate of 96.5% for Leap-Gesture and 97.3% for Manipulation-Gesture. In addition, through the experiment of a flower and plant interaction, our dynamic gesture recognition solution can help users realize the interactive operation accurately and efficiently. In contrast to previous studies, our prototype system provides the users with a new dimension of experience and changes the research model of traditional forestry.

Somatosensory interaction has already become a research focus with the rapid development of virtual reality (VR) technologies, which has been widely applied in the field of computer vision. However, the task is very challenging because of the serious penetrating phenomena in the process of interaction and the high complexity of the gesture recognition problem. For these issues, we present a feasible solution that solves the problem of finger penetration in virtual flower interaction process, which includes the details of virtual hand position mapping, object collision detection, and finger position optimization. After analyzing the requirements associated with hand gesture in virtual flower interaction, we propose a finger gesture-based method to recognize the custom gestures, which utilized Particle Swarm Optimization (PSO) algorithm to optimize the trajectory of fingertips and joints. In addition, a prototype of virtual flower somatosensory interaction system has been designed and implemented for interactive forestry application, and the prototype evaluation has been given through users’ experiments. Experimental results show that the proposed methods can effectively solve the problem of finger penetration during grasping, accurately identify the custom gestures, and provide a more natural, intuitive and efficient user experience compared with the traditional interaction.