Autism Spectrum Disorder is a neurodevelopmental disorder that typically manifests in early childhood, characterized by difficulties in social interaction and communication, narrow interests, and repetitive behaviors. Although there is currently no complete cure, early intervention is crucial for alleviating symptoms and developing skills. The diagnosis of autism is often subjective, time-consuming, and costly. This study proposes a DRD model that combines DenseNet121, ResNet152, and decision tree algorithms, applied to facial images aligned using MTCNN to identify autism. The model achieved 94% accuracy and 0.9768 AUC-ROC on the New-Kaggle dataset, and 98 % accuracy with 0.9948 AUC-ROC on the YTUIA dataset, significantly outperforming the results obtained by using DenseNet121 and ResNet152 models alone. Compared to other studies using facial images to identify autism, our method showed higher recognition accuracy. This suggests that using this approach for screening children with autism is feasible and can offer potential for early detection across large populations.

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition typically emerging in early childhood, characterized by challenges in social interaction, communication deficits, restricted interests, and repetitive behavioral patterns. While no complete cure exists, early intervention remains critical for symptom management and skill development in affected children. Traditional diagnostic approaches depend on clinical assessments by mental health experts following established criteria, yet these methods are constrained by subjectivity, prolonged evaluation periods, and high costs. Aiming at the problem that most of the existing studies use a single deep learning model to classify autistic facial images with insufficient accuracy, this study presents an innovative deep learning framework MFAN that combines pre-trained VGG16 and MobileNetV2 architectures with a Convolutional Block Attention Module (CBAM). By exploiting the discriminative facial features distinguishing autistic and neurotypical individuals, the proposed model aims to classify ASD status using facial images. Evaluation metrics include accuracy, precision, and recall. After rigorous training and validation protocols, the MFAN model achieved 92.67% test accuracy and an AUC-ROC of 0.9635. These results outperform standalone VGG16 and MobileNetV2 models and their simple combinations, demonstrating enhanced classification efficacy. The findings highlight the potential of deep transfer learning for scalable ASD screening, offering a promising tool for early detection in population-level contexts.

Relative radiometric calibration (RRC) mainly focuses on color consistency and streak levels between multi-camera or multiple charge-coupled devices (CCDs), that’s to say, full field-of-view (FOV). But RRC may not be conducted completely or that useful due to some factors, such as data quality or quantity in lifetime image statistics, and ineffective side-slither RRC. Aimed to this, this paper proposes a novel approach to solve inner uneven illumination of each camera image and relative radiometric difference of multi-camera images. The highest layer of unidirectional pyramid (UDP) is decomposed into illumination and reflectance components. Uneven phenomenon in this scale is eliminated in illumination component with column-by-column compensation processing and different scales of non-uniformity are removed together with unidirectional pyramid reconstruction. Radiometric variation of multi-camera images is solved with iterative radiometric adjustment. Some typical data of HISEA-2 Multi-Spectral Scanner 1 (MSS-1) are used to validate the effectiveness of our method both in visual and quantitative terms.

Achieving color consistency is essential for stitching large-area optical satellite imagery. The narrow swath width of individual images, combined with varying acquisition conditions, inherently introduces color differences. These manifest as marked disparities in brightness, color tone, and local contrast, degrading overall regional consistency. Existing methods primarily focus on correcting color inconsistencies between adjacent images, while often overlooking intra-image illumination non-uniformity, thereby propagating radiometric errors into optimization frameworks. Whisk-broom sensors, which can acquire imagery over a much wider swath width along the parallels, frequently exhibit substantial intra-image brightness variations, particularly in high-latitude regions. Compounded by frequent cloud cover and rapid temporal changes of features, extracting reliable color correspondences for optimization becomes intractable. To address these challenges, we propose a novel color correction framework that simultaneously considers intra-image illumination non-uniformity and radiometric variations caused by cloud prevalence and dynamic surface changes. First, a solar elevation angle map is extracted for down-sampled source image based on their geographic metadata and sensor geometry. An inverse compensation based on the normalized sine value of the solar elevation angle is then applied to mitigate brightness disparities caused by varying incident radiance. Second, to address atmospheric effects that vary with wavelength, such as differential absorption and scattering that cause color casts especially in low-illumination regions, a reference spectral channel is selected to guide the correction. Finally, we introduce a hybrid strategy for selecting reliable color correspondences in overlapping regions, using both grayscale and texture similarity under complex coverage conditions. Residual radiometric information is incorporated into a cost function, which jointly considers original color control and overall color balance to enhance the global consistency of the corrected mosaic. Extensive experiments conducted on imagery from the Wide Swath Imager (WSI) of DaQi-1 (DQ-1) and the Chinese Ocean Color and Temperature Scanner (COCTS) of HaiYang-1E (HY-1E) demonstrate that the proposed method effectively removes uneven illumination and color discrepancies. Compared to three state-of-the-art methods, our approach achieves superior performance in both visual quality and quantitative metrics.

The on-board processing systems of high-resolution optical satellites performing hotspot observations must be of high efficiency and high precision. To meet these requirements, a real-time geometric correction (RGC) method was developed based on a target-driven virtual linear-array reimaging (VLR) model. First, the undistorted VLR was used instead of the original distorted physical linear array to achieve a relative orientation of the sub-images of the sensor, ensuring the relative geometric accuracy of the original multilinear array and multiband images. Next, the coordinate position of the region of interest (ROI) in the original image was accurately located in a step-by-step strategy. According to the object-space projection model (OPM) of the VLR and the physical strict model (PSM) of the original image, a coordinate mapping relationship could be established. Finally, the RGC of the ROI image was achieved through GPU-accelerated grayscale resampling. The method was then tested using panchromatic (PAN) and multispectral scanner (MSS) data of LuoJia3-02. The results showed that the processed images exhibited satisfactory band registration accuracy and maintained geometric consistency among various linear-array scanners. Furthermore, in terms of performance, the ROI processing speed was fully adapted to the imaging rate, which fulfilled the real-time on-board processing demands.

Relative radiometric calibration (RRC) is a crucial step in enhancing the quality of satellite images, and it serves as a fundamental technology to ensure the reliability of information extracted from these images. Traditional side-slither RRC methods typically use homogeneous scenes as imaging sites to ensure approximately identical input for detectors of multiple non-collinear time-delay integration-charge-coupled devices (TDI-CCDs). However, as spatial resolution improves, the demand for site uniformity is increasing, limiting the application of these traditional methods. Therefore, we propose a push-broom data-aided side-slither RRC method, which involves sequential calibration of a single TDI-CCD and an entire field of view (FOV). The first step is designed to eliminate response differences within each TDI-CCD, while the latter incorporates push-broom data to determine the adjacent radiometric relationship via adjustment with maximum standard deviation preservation (MSDP). Experiments show that our method has achieved better results in both visual effect and quantitative assessment, compared with the other two advanced RRC methods.

Geometric calibration (GC) is a technique to compensate for the systematic errors in the imaging model of an optical satellite. The independent GC method without use of ground calibration site has been studied in recent years. In this paper, an integrated independent method aiming to the GC of stereo cameras aboard an optical satellite is presented. Supported by the satellite's stereo imaging ability, this method can overcome the strong correlation between the elevation error and camera GC accuracy, and get rid of the dependency on the constraints of ground elevation further. The real data collected by the stereo three-linear camera (TLC) of ZY-3 satellite was used to verify this method. The satisfactory GC accuracy better than 1 pixel indicated that the presented method effectively compensated for systematic errors, and improved the geometric quality of TLC images together.

In this letter, we study the linear processing method to alleviate the intercarrier interference (ICI) for the orthogonal frequency division multiplexing (OFDM) index modulation (IM) in the rapidly time-varying (RTV) channel. Concretely, the proposed linear processing scheme is implemented by the joint design of the transmit precoding and receive postprocessing matrices. First, a lower bound of the capacity of OFDM-IM in the RTV channel is derived. Then, the precoding and postprocessing matrices are designed to maximize this capacity lower bound through utilizing the particle swarm optimization algorithm. Computer simulations show that the proposed scheme can alleviate the ICI effectively and has better performance than the conventional ICI self-cancellation scheme.