This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its practical utility using a real drone-collected dataset. A thermal dataset was developed from drone-collected imagery and was used to fine-tune VLMs through multimodal projector alignment, enabling the transfer of information from RGB-based visual representations to thermal radiometric inputs. Three representative models, including InternVL3-8B-Instruct, Qwen2.5-VL-7B-Instruct, and Qwen3-VL-8B-Instruct, were benchmarked under both closed-set and open-set prompting conditions for species recognition and instance enumeration. Among the tested models, Qwen3-VL-8B-Instruct with open-set prompting achieved the best overall performance, with F1 scores of 0.935 for deer, 0.915 for rhino, and 0.968 for elephant, and within-1 enumeration accuracies of 0.779, 0.982, and 1.000, respectively. In addition, combining thermal imagery with simultaneously collected RGB imagery enabled the model to generate habitat-context information, including land-cover characteristics, key landscape features, and visible human disturbance. Overall, the findings demonstrate that lightweight projector-based adaptation provides an effective and practical route for transferring RGB-pretrained VLMs to thermal drone imagery, expanding their utility from object-level recognition to habitat-context interpretation in ecological monitoring.

翻译：本研究提出了一种轻量级多模态适配框架，以弥合基于RGB预训练的视觉语言模型与热红外图像之间的表征差距，并通过真实无人机采集数据集验证其实用价值。基于无人机航拍图像构建了热红外数据集，通过多模态投影仪对齐方式微调视觉语言模型，实现了从RGB视觉表征到热辐射输入的信息迁移。在封闭集与开放集提示条件下，对InternVL3-8B-Instruct、Qwen2.5-VL-7B-Instruct和Qwen3-VL-8B-Instruct三种代表性模型进行了物种识别与个体计数基准测试。在测试模型中，采用开放集提示的Qwen3-VL-8B-Instruct表现最优，鹿、犀牛和大象识别的F1分数分别达到0.935、0.915和0.968，计数误差≤1的准确率分别为0.779、0.982和1.000。此外，将热红外图像与同步采集的RGB图像结合，使模型能够生成栖息地环境信息，包括土地覆盖特征、关键景观要素及可见人为干扰。总体而言，研究结果表明，基于轻量级投影仪适配的方法为将RGB预训练视觉语言模型迁移至热红外无人机图像提供了有效且实用的路径，将该类模型的应用范围从目标级识别拓展至生态监测中的栖息地环境解释。