Search Results (3)

Accurate food mass estimation is a key component of automated calorie estimation tools, and there is growing interest in leveraging image analysis for this purpose due to its ease of use and scalability. However, current methods face important limitations. Some rely on 3D sensors for depth estimation, which are not widely accessible to all users, while others depend on camera intrinsic parameters to estimate volume, reducing their adaptability across different devices. Furthermore, AI-based approaches that bypass these parameters often struggle with generalizability when applied to images captured using diverse sensors or camera settings. To overcome these challenges, we introduce a three-stage, transformer-based method for estimating food mass from RGB images, balancing accuracy, computational efficiency, and scalability. The first stage applies the Segment Anything Model (SAM 2) to segment food items in images from the SUECFood dataset. Next, we use the Global-Local Path Network (GLPN) to perform monocular depth estimation (MDE) on the Nutrition5k dataset, inferring depth information from a single image. These outputs are then combined through alpha compositing to generate enhanced composite images with precise object boundaries. Finally, a Vision Transformer (ViT) model processes the composite images to estimate food mass by extracting relevant visual and spatial features. Our method achieves notable improvements in accuracy compared to previous approaches, with a mean squared error (MSE) of 5.61 and a mean absolute error (MAE) of 1.07. Notably, this pipeline does not require specialized hardware like depth sensors or multi-view imaging, making it well-suited for practical deployment. Future work will explore the integration of ingredient recognition to support a more comprehensive dietary assessment system. Full article

In view of the problems in planning and recommending tour routes, this paper constructs a feature text mining (FTM) method and spatial accessibility model (SAM) as the key factors for scenic spot recommendation (SSR) and tour route recommendation (TRR). The scenic spot clustering algorithm (SSCA) based on FTM was constructed by tourists’ text evaluation data mining. Considering the spatial attributes of scenic spots, the scenic spot topology tree algorithm (SSTTA) based on dynamic buffer spatial accessibility (DBSA) was constructed. The optimal scenic spots were recommended based on interest matching and spatial accessibility optimization. As to the recommended scenic spots, this paper proposes an optimal tour route recommendation algorithm (TRRA) based on SSTTA, which aims to determine the optimal adjacent section path structure tree (ASPST) with the lowest cost under travel constraints and transportation modes. The experiment verifies that the proposed algorithm can recommend scenic spots that match tourists’ interests and have optimal spatial accessibility, and the optimal tour routes with the lowest costs under certain travel constraints. Compared with the searched sub-optimal tour routes, the optimal tour route recommended by the proposed algorithm produces the lowest travel costs, and all the scenic spots in the tour route meet the tourists’ interests. Compared with the commonly used BDMA and GDMA methods, the proposed algorithm can determine the optimal routes with lower travel costs. Full article

Access to high spatial resolution satellite images enables more accurate and detailed analysis of these images. Furthermore, it facilitates easier decision-making on a wide range of issues. Nevertheless, there are commercial satellites such as Worldview that have provided a spatial resolution of fewer than 2.0 m, but using them for large areas or multi-temporal analysis of an area brings huge costs. Thus, to tackle these limitations and access free satellite images with a higher spatial resolution, there are challenges that are known as single-image super-resolution (SISR). The Sentinel-2 satellites were launched by the European Space Agency (ESA) to monitor the Earth, which has enabled access to free multi-spectral images, five-day time coverage, and global spatial coverage to be among the achievements of this launch. Also, it led to the creation of a new flow in the field of space businesses. These satellites have provided bands with various spatial resolutions, and the Red, Green, Blue, and NIR bands have the highest spatial resolution by 10 m. In this study, therefore, to recover high-frequency details, increase the spatial resolution, and cut down costs, Sentinel-2 images have been considered. Additionally, a model based on Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) has been introduced to increase the resolution of 10 m RGB bands to 2.5 m. In the proposed model, several spatial features were extracted to prevent pixelation in the super-resolved image and were utilized in the model computations. Also, since there is no way to obtain higher-resolution (HR) images in the conditions of the Sentinel-2 acquisition image, we preferred to simulate data instead, using a sensor with a higher spatial resolution that is similar in spectral bands to Sentinel-2 as a reference and HR image. Hence, Sentinel-Worldview image pairs were prepared, and the network was trained. Finally, the evaluation of the results obtained showed that while maintaining the visual appearance, it was able to maintain some spectral features of the image as well. The average Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Spectral Angle Mapper (SAM) metrics of the proposed model from the test dataset were 37.23 dB, 0.92, and 0.10 radians, respectively. Full article