Search

Higher standards have been proposed for detection systems since camouflaged objects are not distinct enough, making it possible to ignore the difference between their background and foreground. In this paper, we present a new framework for Camouflaged Object Detection (COD) named FSANet, which consists mainly of three operations: spatial detail mining (SDM), cross-scale feature combination (CFC), and hierarchical feature aggregation decoder (HFAD). The framework simulates the three-stage detection process of the human visual mechanism when observing a camouflaged scene. Specifically, we have extracted five feature layers using the backbone and divided them into two parts with the second layer as the boundary. The SDM module simulates the human cursory inspection of the camouflaged objects to gather spatial details (such as edge, texture, etc.) and fuses the features to create a cursory impression. The CFC module is used to observe high-level features from various viewing angles and extracts the same features by thoroughly filtering features of various levels. We also design side-join multiplication in the CFC module to avoid detail distortion and use feature element-wise multiplication to filter out noise. Finally, we construct an HFAD module to deeply mine effective features from these two stages, direct the fusion of low-level features using high-level semantic knowledge, and improve the camouflage map using hierarchical cascade technology. Compared to the nineteen deep-learning-based methods in terms of seven widely used metrics, our proposed framework has clear advantages on four public COD datasets, demonstrating the effectiveness and superiority of our model.

Biostimulants can enhance horticultural crop production. However, their application in hydroponically grown lettuce is still limited, and information regarding their relative efficacy is lacking. A greenhouse trial was conducted to address this issue. Five nutrient solution treatments were evaluated on two lettuce cultivars: butterhead and red oak-leaf. The treatments included a half-strength modified Hoagland solution (Hs-H); a full-strength modified Hoagland solution (Fs-H); and Hs-H supplemented with 50 mg L−1 fulvic acid (FA), 334 mg L−1 seaweed extract (SE), or 5 mL L−1 gamma polyglutamic acid (PGA). The results indicated that the shoot biomass observed after biostimulant supplementation was significantly greater than or comparable to that observed with Fs-H. Nutrient solutions supplemented with SE and PGA led to a greater increase in the root biomass than that realized with Hs-H and Fs-H treatments. The Hs-H + FA treatment resulted in the lowest root-to-shoot ratio on a fresh weight basis among all treatments. The nitrate concentration in the shoot was significantly reduced following biostimulant supplementation compared to that realized with Fs-H and Hs-H treatments. Nutrient solutions supplemented with SE and PGA also decreased soluble sugar concentrations compared to that achieved using Hs-H and Fs-H treatments. FA and SE improved nutrient uptake for both cultivars, but PGA had a minimal effect on nutrient uptake. The two cultivars varied in their responses to biostimulant supplementation with regard to biomass, quality traits, and nutrient uptake. This study supports using fulvic acid and seaweed extract, rather than γ-PGA, in hydroponic lettuce production systems.