No abstract

No abstract

Detecting small objects such as vehicles in satellite images is a difficult problem. Many features (such as histogram of oriented gradient, local binary pattern, scale-invariant feature transform, etc.) have been used to improve the performance of object detection, but mostly in simple environments such as those on roads. Kembhavi et al. proposed that no satisfactory accuracy has been achieved in complex environments such as the City of San Francisco. Deep convolutional neural networks (DNNs) can learn rich features from the training data automatically and has achieved state-of-the-art performance in many image classification databases. Though the DNN has shown robustness to distortion, it only extracts features of the same scale, and hence is insufficient to tolerate large-scale variance of object. In this letter, we present a hybrid DNN (HDNN), by dividing the maps of the last convolutional layer and the maxpooling layer of DNN into multiple blocks of variable receptive field sizes or max-pooling field sizes, to enable the HDNN to extract variable-scale features. Comparative experimental results indicate that our proposed HDNN significantly outperforms the traditional DNN on vehicle detection.

Vibrio parahaemolyticus (V. parahaemolyticus), which may cause gastrointestinal disorders in humans, is a pathogen commonly found in seafood. There are many methods for detecting V. parahaemolyticus, yet they have some shortcomings, such as high cost, labor-intensiveness, and complicated operation, which are impractical for resource-limited settings. Herein, we present a sequence-specific, label-free, and colorimetric method for visual detection of V. parahaemolyticus. This method utilizes CRISPR/ Cas12a to specifically recognize the loop-mediated isothermal amplification (LAMP) products for further trans-cleaving the Gquadruplex DNAzyme and depriving its peroxidase-mimicking activity. In this way, the results can be directly observed with the naked eyes via the color development of 2,2′-azino-di-(3-ethylbenzthiazoline-6-sulfonic acid) (ABTS 2− ), which displays colorless for positive samples while green for target-free samples. We term such Cas12a−crRNA preventing ABTS 2− from developing color by trimming the G-quadruplex DNAzyme as Cascade. The proposed method can detect 9.8 CFU (per reaction) of pure cultured V. parahaemolyticus, and the sensitivity is comparable to real-time LAMP. It has been applied for practical use and showed the capability to detect 6.1 × 10 2 CFU/mL V. parahaemolyticus in shrimp samples. Based on this, the newly established Cascade method can be employed as a universal biosensing strategy for pathogenic bacterial testing in the field.