Aerial visible-to-infrared image translation expands infrared datasets by generating infrared images from visible images for various applications in aerial remote sensing. However, existing image translation methods do not consistently produce high-quality results for each image. In practice, it is crucial to evaluate and filter for high-quality generated images to ensure they are suitable for subsequent tasks. Additionally, generated images often lack paired data for effective evaluation. In this letter, we propose patch grid-based quality assessment (PGQA) for assessing the quality of translated infrared images from visible images in aerial remote sensing. This method decomposes global authenticity and similarity into local authenticity and similarity because the lack of paired data makes it difficult to assess the authenticity of a picture. Specifically, the method first grids real infrared images and trains them with convolutional autoencoder (CAE) networks. Similar components and contents naturally share similar feature representations, so the generated infrared images are fed into the trained autoencoder model by the same grid operation. If the average reconstruction loss is lower, the image quality is higher. This approach enables effective quality assessment of generated infrared images and is consistent with other paired methods. It enhances the utility of generated images and increases their practical value in deep learning applications. The source code is available athttps://github.com/fan-lmw/PGQA.git.

In object detection, the cost of labeling is very high because it needs not only to confirm the categories of multiple objects in an image but also to determine the bounding boxes of each object accurately. Thus, integrating active learning into object detection will raise pretty positive significance. In this paper, we propose a classification committee for the active deep object detection method by introducing a discrepancy mechanism of multiple classifiers for samples' selection when training object detectors. The model contains a main detector and a classification committee. The main detector denotes the target object detector trained from a labeled pool composed of the selected informative images. The role of the classification committee is to select the most informative images according to their uncertainty values from the view of classification, which is expected to focus more on the discrepancy and representative of instances. Specifically, they compute the uncertainty for a specified instance within the image by measuring its discrepancy output by the committee pre-trained via the proposed Maximum Classifiers Discrepancy Group Loss (MCDGL). The most informative images are finally determined by selecting the ones with many high-uncertainty instances. Besides, to mitigate the impact of interference instances, we design a Focusing on Positive Instances Loss (FPIL) to provide the committee the ability to automatically focus on the representative instances as well as precisely encode their discrepancies for the same instance. Experiments are conducted on Pascal VOC and COCO datasets versus some popular object detectors. And results show that our method outperforms the state-of-the-art active learning methods, which verifies the effectiveness of the proposed method.

Translating readily available visible (VIS) images into thermal infrared (TIR) images effectively alleviates the shortage of TIR data. While current methods have yielded commendable results, they fall short in generating diverse and realistic thermal infrared images, primarily due to insufficient consideration of temperature variations. In this paper, we propose a Thermally Controlled GAN (TC-GAN) that leverages VIS images to generate diverse TIR images, with the ability to control the relative temperatures of multiple objects, particularly those with temperature variations. Firstly, we introduce the physical coding module, which employs a conditional variational autoencoder GAN to learn the distributions of relative temperature information for the objects and environmental state information. Then, the physical information can be obtained by sampling the distribution. When this information is fused with the visible image, it facilitates the generation of diverse TIR images. To ensure authenticity and strengthen the physical constraints across different regions of the image, we introduce a self-attention mechanism in the generator that prioritizes the relative temperature relationships within the image. Additionally, we utilize a local discriminator that focuses on objects with actively changing temperatures and their interactions with the surrounding environment, thereby reducing the discontinuity between the target and the background. Experiments on the Drone Vehicle and AVIID datasets show that our approach outperforms mainstream diversity generation methods in terms of authenticity and diversity.