Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

Prediction model on hydrolysis kinetics of phthalate monoester:A density functional theory study

As primary degradation products of phthalate esters,phthalate monoesters(MPEs)have been widely detected in various aquatic environments and drawn growing toxicological concerns.Hydrolysis kinetics that is of importance for assessing environmental persistence of chemicals remain elusive for MPEs.Herein,kinetics of base-catalyzed and neutral hydrolysis for 18 MPEs with different leaving groups was investigated by density functional theory calculation.Results indicate that MPEs with leaving groups having p Kaof<10 prefer dissociative transition states.MPEs are more persistent than their parents,and their hydrolysis half-lives were calculated to vary from 3.4 min to 79.2 years(p H=7–9).A quantitative structure-activity relationship model was developed for predicting the hydrolysis kinetics parameters.It was found that p Kaof the leaving groups and electronegativity of the MPEs are key factors determining the hydrolysis kinetics.This work may lay a theoretical foundation for better understanding the chemical process that governs MPE persistence in aquatic environments.

Biogenic volatile organic compound emissions from leaves and fruits of apple and peach trees during fruit development

Biogenic volatile organic compounds(BVOCs)are widely involved in a variety of atmospheric chemical processes due to their high reactivity and species diversity.To date,however,research on BVOCs in agroecosystems,particularly fruit trees,remains scarce despite their large cultivation area and economic interest.BVOC emissions from different organs(leaf or fruit)of apple and peach trees were investigated throughout the stages of fruit development(FS,fruit swelling;FC,fruit coloration;FM,fruit maturity;and FP,fruit postharvest)using a proton-transfer-reaction mass spectrometer.Results indicated that methanol was the most abundant compound emitted by the leaf(apple tree leaf 492.5±47.9 ng/(g·hr),peach tree leaf 938.8±154.5 ng/(g·hr)),followed by acetic acid and green leaf volatiles.Beside the above three compounds,acetaldehyde had an important contribution to the emissions from the fruit.Overall,the total BVOCs(sum of eight compounds studied in this paper)emitted by both leaf and fruit gradually decreased along the fruit development,although the effect was significant only for the leaf.The leaf(2020.8±258.8 ng/(g·hr))was a stronger BVOC emitter than the fruit(146.0±45.7 ng/(g·hr))(P=0.006),and there were no significant differences in total BVOC emission rates between apple and peach trees.These findings contribute to our understanding on BVOC emissions from different plant organs and provide important insights into the variation of BVOC emissions across different fruit developmental stages.