Abstract:Fragrant rosewood (Dalbergia odorifera T.C. Chen) is a highly-valued species suffering from vulnerability due to over-development for wood and medicine. In this study, Fragrant rosewood seedlings were cultured with chitosan oligosaccharide (CO) addition at rates of 0 and 1/800 (v/v) under artificial lightings by 200-W high-pressure sodium (HPS) lamps and 280-W light-emitting diode (LED) panels for a 15 h daily photoperiod and a natural illumination as the control. The LEDs were designed to emit lights in 85% of red (600-700 nm), 15% of green(500-600 nm), and 5% of blue (400-500 nm). The height of artificial lightings was elevated every five to seven days to keep the mean photosynthetic photon flux density (PPFD) of 72-73 µmol m −2 s −1 of artificial lighting at shoot-tips. Seedlings under LED lighting with CO addition had the greatest diameter growth and leaf biomass, as well as the highest nutrient utilization and evaluated quality, while those under HPS lighting had a higher stem sugar concentration but unchanged shoot growth and biomass compared to the control. In conclusion, we recommend Fragrant rosewood seedlings to be cultured with CO addition under LED lighting to efficiently promote synthetic quality and nutrient utilization.

Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance for tiny object detection. Specifically, we first model the bounding boxes as 2D Gaussian distributions and then propose a new metric dubbed Normalized Wasserstein Distance (NWD) to compute the similarity between them by their corresponding Gaussian distributions. The proposed NWD metric can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric. We evaluate our metric on a new dataset for tiny object detection (AI-TOD) in which the average object size is much smaller than existing object detection datasets. Extensive experiments show that, when equipped with NWD metric, our approach yields performance that is 6.7 AP points higher than a standard fine-tuning baseline, and 6.0 AP points higher than state-of-the-art competitors.

No abstract

Object detection in aerial images is a fundamental yet challenging task in remote sensing field. As most objects in aerial images are in arbitrary orientations, oriented bounding boxes (OBBs) have a great superiority compared with traditional horizontal bounding boxes (HBBs). However, the regression-based OBB detection methods always suffer from ambiguity in the definition of learning targets, which will decrease the detection accuracy. In this paper, we provide a comprehensive analysis of OBB representations and cast the OBB regression as a pixel-level classification problem, which can largely eliminate the ambiguity. The predicted masks are subsequently used to generate OBBs. To handle huge scale changes of objects in aerial images, an Inception Lateral Connection Network (ILCN) is utilized to enhance the Feature Pyramid Network (FPN). Furthermore, a Semantic Attention Network (SAN) is adopted to provide the semantic feature, which can help distinguish the object of interest from the cluttered background effectively. Empirical studies show that the entire method is simple yet efficient. Experimental results on two widely used datasets, i.e., DOTA and HRSC2016, demonstrate that the proposed method outperforms state-of-the-art methods.

No abstract