Wild birds are monitored with the important objectives of identifying their habitats and estimating the size of their populations. Especially in the case of migratory bird, they are significantly recorded during specific periods of time to forecast any possible spread of animal disease such as avian influenza. This study led to the construction of deep-learning-based object-detection models with the aid of aerial photographs collected by an unmanned aerial vehicle (UAV). The dataset containing the aerial photographs includes diverse images of birds in various bird habitats and in the vicinity of lakes and on farmland. In addition, aerial images of bird decoys are captured to achieve various bird patterns and more accurate bird information. Bird detection models such as Faster Region-based Convolutional Neural Network (R-CNN), Region-based Fully Convolutional Network (R-FCN), Single Shot MultiBox Detector (SSD), Retinanet, and You Only Look Once (YOLO) were created and the performance of all models was estimated by comparing their computing speed and average precision. The test results show Faster R-CNN to be the most accurate and YOLO to be the fastest among the models. The combined results demonstrate that the use of deep-learning-based detection methods in combination with UAV aerial imagery is fairly suitable for bird detection in various environments.

Citrus fruits were sorted based on external qualities, such as size, weight, and color, and internal qualities, such as soluble solid content (SSC), acidity, and firmness. Visible and near-infrared (VNIR) hyperspectral imaging techniques were used as rapid and nondestructive techniques for determining the internal quality of fruits. The applicability of the VNIR hyperspectral imaging technique for predicting the SSC in citrus fruits was evaluated in this study. A VNIR hyperspectral imaging system with a wavelength range of 400–1000 nm and 100 W light source was used to acquire hyperspectral images from citrus fruits in two orientations (i.e., stem and calyx ends). The SSC prediction model was developed using partial least-squares regression (PLSR). Spectrum preprocessing, effective wavelength selection through competitive adaptive reweighted sampling (CARS), and outlier detection were used to improve the model performance. The performance of each model was evaluated using the coefficient of determination (R²) and root mean square error (RMSE). In the present study, the PLSR model was developed using only a citrus cultivar. The SSC prediction CARS-PLSR model with outliers removed exhibited R² and RMSE values of approximatively 0.75 and 0.56 °Brix, respectively. The results of this study are expected to be useful in similar fields such as agricultural and food post-harvest management, as well as in the development of an online system for determining the SSC of citrus fruits.

Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium) on the surface of food processing facilities by using fluorescence hyperspectral imaging. E. coli and S. typhimurium were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, k-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for E. coli (1–4 log CFU·cm⁻²) and S. typhimurium (1–6 log CFU·cm⁻²) were over 90% for most machine learning models used, and the highest performances were generally obtained from the k-nearest neighbor (k-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images.

A Tungsten-Halogen (TH) lamp is the most popular light source in NIR spectroscopy and hyperspectral imaging, which requires a warm-up to reach very high temperatures of up to 250 °C and take a long time for radiation stabilization. Consequently, it has a large enough volume to enable heat dissipation to prevent the thermal runaway of the electric circuit and turn out its power efficiency very low. These are major barriers for miniaturizing spectral systems and hyperspectral imaging devices. However, TH lamps can be replaced by pc-NIR LEDs in order to avoid high temperature and large volume. We compared the spectral emission of the available commercial pc-NIR LEDs under the same condition. As a replacement for the TH lamp, the VIS + NIR LED module was developed to combine a warm-white LED and pc-NIR LEDs. In order to feature out the availability of the VIS + NIR LED module against the TH lamp, they were used as the light source for evaluating the Soluble Solid Content (SSC) of an apple through VIS-NIR spectroscopy. The results show a remarkable feasibility in the performance of the partial least square (PLS) model using the VIS + NIR LED module; during PLS calibration, the correlation coefficient (R) values are 0.664 and 0.701, and the Mean Square Error (MSE) values are 0.681 and 0.602 for the TH lamp and VIS + NIR LED module, respectively. In VIS-NIR spectroscopy, this study indicates that the TH lamp could be replaceable with a warm-white LED and pc-NIR LEDs.