Lightweight helmet target detection algorithm combined with Effici-Bi-Level Routing Attention.

Wearing helmets is essential in two-wheeler traffic to reduce the incidence of injuries caused by accidents. We present FB-YOLOv7, an improved detection network based on the YOLOv7-tiny model. The objective of this network is to tackle the problems of both missed detection and false detection that result from the difficulties in identifying small targets and the constraints in equipment performance during helmet detection. By applying an enhanced Bi-Level Routing Attention, the network can improve its capacity to extract global characteristics and reduce information distortion. Furthermore, we deploy the AFPN framework and effectively resolve information conflict using asymptotic adaptive feature fusion technology. Incorporating the EfficiCIoU loss significantly improves the prediction box's accuracy. Experimental trials done on specific datasets reveal that FB-YOLOv7 attains an accuracy of 87.2% and 94.6% on the mean average precision (mAP@.5). Additionally, it maintains a high level of efficiency with frame rates of 129 and 126 frames per second (FPS). FB-YOLOv7 surpasses the other six widely-used detection networks in terms of detection accuracy, network implementation requirements, sensitivity in detecting small targets, and potential for practical applications.

Changes in the concentration of air pollutants before and after the COVID-19 blockade period and their correlation with vegetation coverage.

In order to control the spread of COVID-19, China had implemented strict lockdown measures. The closure of cities had had a huge impact on human production and consumption activities, which had greatly reduced population mobility. This article used air pollutant data from 341 cities in mainland China and divided these cities into seven major regions based on geographic conditions and climatic environment. The impact of urban blockade on air quality during COVID-19 was studied from the perspectives of time, space, and season. In addition, this article used Normalized Difference Vegetation Index (NDVI) to systematically analyze the characteristics of air pollution in the country and used the Pearson correlation coefficient to explore the relationship between NDVI and the air pollutant concentrations during the COVID-19 period. Then, linear regression was used to find the quantitative relationship between NDVI and AQI, and the fitting effect of the model was found to be significant through t test. Finally, some countermeasures were proposed based on the analysis results, and suggestions were provided for improving air quality. This paper has drawn the following conclusions: (1) the concentration of pollutants varied greatly in different regions, and the causes of their pollution sources were also different. The region with the largest decline in AQI was the Northeast China (60.01%), while the AQI in the southwest China had the smallest change range, and its value had increased by 1.72%. In addition, after the implementation of the city blockade, the concentration of NO2 in different regions dropped the most, but the increase in O3 was more obvious. (2) Higher vegetation coverage would have a beneficial impact on the atmospheric environment. Areas with higher NDVI values have relatively low AQI. There is a negative correlation between NDVI and AQI, and an average increase of 0.1 in NDVI will reduce AQI by 3.75 (95% confidence interval). In the case of less human intervention, the higher the vegetation coverage, the lower the local pollutant concentration will be. Therefore, the degree of vegetation coverage would have a direct or indirect impact on air pollution.

Robust Visual Ship Tracking with an Ensemble Framework via Multi-View Learning and Wavelet Filter.

Maritime surveillance videos provide crucial on-spot kinematic traffic information (traffic volume, ship speeds, headings, etc.) for varied traffic participants (maritime regulation departments, ship crew, ship owners, etc.) which greatly benefits automated maritime situational awareness and maritime safety improvement. Conventional models heavily rely on visual ship features for the purpose of tracking ships from maritime image sequences which may contain arbitrary tracking oscillations. To address this issue, we propose an ensemble ship tracking framework with a multi-view learning algorithm and wavelet filter model. First, the proposed model samples ship candidates with a particle filter following the sequential importance sampling rule. Second, we propose a multi-view learning algorithm to obtain raw ship tracking results in two steps: extracting a group of distinct ship contour relevant features (i.e., Laplacian of Gaussian, local binary pattern, Gabor filter, histogram of oriented gradient, and canny descriptors) and learning high-level intrinsic ship features by jointly exploiting underlying relationships shared by each type of ship contour features. Third, with the help of the wavelet filter, we performed a data quality control procedure to identify abnormal oscillations in the ship positions which were further corrected to generate the final ship tracking results. We demonstrate the proposed ship tracker's performance on typical maritime traffic scenarios through four maritime surveillance videos.