In order to acquire multispectral images precisely and quickly, a four-band multispectral capturing system with one imaging sensor is designed and evaluated in this paper. Firstly, four imaging bands are arranged in a 2×2 multispectral filter array(MSFA), and their filter spectral transmittances within the visual wavelength are designed uniformly. Then, the mosaicked four-band image is generated on the single-sensor according to the designed MSFA. In order to recover the mosaicked images, a demosaicking algorithm based on constant hue assumption is employed to highly maintain the image edges. At last, the four-band spectral capturing system is characterized by using the calibration target Macbeth Colorchecker,, and a linear relationship between the band values and spectrum are calculated based on polynomial regression method, afterwards the demosaicked four-band pixels can be converted into the multispectral reflectance with that obtained relationship. In the experiment, the four-band multispectral imaging system with the proposed demosaicking algorithm is evaluated, and the experiment result demonstrates the proposed algorithm outperform the other methods in PSNR and RRMS.

No abstract

With the development of Earth observation technology, more multisource remote sensing (RS) images are obtained from various satellite sensors and significantly enrich the data source of change detection (CD). However, the utilization of multisource bitemporal images frequently introduces challenges during featuring or representing the various physical mechanisms of the observed landscapes and makes it more difficult to develop a general model for homogeneous and heterogeneous CD adaptively. In this article, we propose an adaptive spatial-spectral transformer change detection network based on spectral token guidance, named STCD-Former. Specifically, a spectral transformer with dual-branch first encodes the diverse spectral sequence in spectral-wise to generate a corresponding spectral token. And then, the spectral token is used as guidance to interact with the patch token to learn the change rules. More significantly, to optimize the learning of difference information, we design a difference amplification module to highlight discriminative features by adaptively integrating the difference information into the feature embedding. Finally, the binary CD result is obtained by multilayer perceptron (MLP). The experimental results on three homogeneous datasets and one heterogeneous dataset have demonstrated that the proposed STCD-Former outperforms the other state-of-the-art methods qualitatively and visually.

No abstract

Crowd understanding and analysis have received increasing attention for couples of decades, and development of human behaviour recognition strongly supports the application of crowd understanding and analysis. Human behaviour recognition usually seeks to automatically analyse ongoing movements and actions in different camera views by using various machine learning methodologies in unknown video clips or image sequences. Compared to other data modalities such as documents and images, processing video data demands much higher computational and storage resources. The idea of using middle level semantic concepts to represent human actions from videos is explored and it is argued that these semantic attributes enable the construction of more descriptive methods for human action recognition. The mid-level attributes, initialized by a cluster processing, are built upon low level features and fully utilize the discrepancies in different action classes, which can capture the importance of each attribute for each action class. In this way, the representation is constructed to be semantically rich and capable of highly discriminative performance even paired with simple linear classifiers. The method is verified on three challenging datasets (KTH, UCF50 and HMDB51), and the experimental results demonstrate that our method achieves better results than the baseline methods on human action recognition.