Hyperspectral transmission imaging may provide a means for rapid screening of breast tumors, but tissue has a strong nature of scattering, thus causing great difficulty in identifying heterogeneity. In this paper, a combination of frame accumulation and deep learning was proposed to detect heterogeneity, and we designed the simulation experiment of collecting phantom images. On the basis of frame accumulation preprocessing, heterogeneous detection is performed on multispectral images by using Faster R-CNN (Faster Regions with Convolutional Neural Networks features) and SSD (Single Shot MultiBox Detector), two typical detection frameworks of deep learning. The results show that the mAP of Faster R-CNN and SSD reach 90.8% and 95.1% respectively when 3 classes (including background) are detected with the help of the dataset provided in the paper, and the mAP (mean Average Precision) of two frameworks both reach 99.9% when 2 classes (including background) are detected. The detection efficiency of SSD is higher than Faster, SSD’s detection speed can reach 50fps, and the detection accuracy of the images after frame accumulation preprocessing is higher than that without frame accumulation processing. In summary, we validate the possibility of employing Faster R-CNN and SSD to detect heterogeneity in multispectral images based on frame accumulation that improves image grayscale resolution, and it has a certain degree of reference significance for the application of deep learning in multispectral image detection.

In this era of artificial intelligence (AI), the Internet of things (IoT) with the capability of connecting a great number of heterogeneous terminals and the popularity of mobile devices, which makes more devices available as another pair of eyes for people, such as video surveillance and smart navigation. As image enhancement is assisting people to better work together and helping people live a smarter life, it is therefore becoming increasingly important. Nevertheless, many vision systems are sensitive to factors like the scattering of light or motion which may cause blur. This paper promotes an image enhancement method and is dedicated to reduce the adverse effects of blurred images on vision systems. We first researched the theory of indented frame over fusion (IFOF) and presented an automatic screening function. Then subtly combined color reversal, registration and transformation. Lastly, we tested two examples with this method and gained good results. Image processed by this method, facing strong scattering of light environment, has improved its quality and visual effects. With the development of this kind of technology, there will be more practical and intelligent applications in our lives, such as license plate numbers recognition in bad weather and important items search on fire scenes.

Hazardous gas leaks are a major trigger of chemical incidents. If not handled in time, they can easily lead to secondary disasters such as fires and explosions. In recent years, with the construction of hazardous chemical monitoring and early-warning systems in China, large volumes of field operating data from flammable and toxic gas sensors have been accumulated, providing a data foundation for leak-pattern studies grounded in real-world scenarios. In this study, 56 leak samples verified by site feedback were selected. Time-aware interpolation and Z-score normalization were used for preprocessing, and time-series features—including standard deviation of first differences, autocorrelation coefficients, and frequency-domain energy—were extracted. Leak patterns were then identified using two unsupervised approaches: K-Means clustering and a 1D-CNN autoencoder. Results show that K-Means effectively distinguishes macro-patterns such as sustained leaks, instantaneous leaks, fluctuating leaks, and interrupted leaks, while the autoencoder demonstrates stronger capability in extracting temporal features, revealing leak evolution and transition characteristics. The two methods are complementary and together provide a viable route to developing an end-to-end model for leak scenario identification and risk discrimination. This work not only verifies the feasibility of conducting leak-pattern recognition using real GDS data but also offers technical guidance for the intelligent upgrading of hazardous chemical monitoring and early-warning systems.