Objective: The objective of this study is to develop a novel algorithm on a mobile system that can warn drivers about the possibility of a collision with a pedestrian. The constraints of the algorithm are near-real-time detection speed and a good detection rate.
Method: Histogram of gradients (HOG)-based detection is widely used in pedestrian safety applications; however, it has low detection speed for real-time systems. Hence, it has no direct usage for mobile systems. In order to achieve near-real-time detection speed, partial Haar transform predetections are applied to an image before HOG detection. The partial and HOG detections are merged and a score-based confidence level is defined for the final detection phase. In this way, the outcome is prioritized and different warning levels can be issued to warn the driver before a possible pedestrian collision.
Results: The proposed algorithm provides an increase in detection speed (from 46 to 76 fps) and detection rate (from 80 to 91%) with respect to HOG-based pedestrian detection. It also improves confidence of the results by multidetection merging and score assignment to detections.
Conclusions: Performance improvement of the algorithm is compared with respect to state-of-the-art detectors/algorithms. Based on the detection rate and detection speed performance, it can be concluded that the proposed algorithm is suitable to be used for mobile systems to warn drivers about the possibility of collision with a pedestrian. 相似文献
Introduction: Young workers are especially vulnerable to occupational injuries and illnesses. There is a continued need to investigate injury burden among young workers across demographics and industry to inform targeted interventions. Workers compensation (WC) claims are important for quantifying work-related injuries and illnesses, however published studies have focused on disabling claims. This study extended previous research on Oregon young workers by including the most recent WC claims data to identify patterns of injury and high risk industries. Methods: We obtained all accepted disabling claims (N = 13,360) and a significant portion of non-disabling claims (N = 24,660) on workers aged 24 years and under from 2013 to 2018. Claim count, rate and cost were calculated by year, age, gender, industry, and injury type. A prevention index (PI) method was used to rank industries in order to inform prevention efforts. Results: Average annual disabling and non-disabling claim rates were 111.6 and 401.3 per 10,000 young workers. Workers aged 19–21 (disabling: 119.0 per 10,000 and non-disabling: 429.3) and 22–24 years (115.7 and 396.4) and male workers (145.3 and 509.0) had higher claim rates than workers aged 14–18 (80.6 and 297.0) and female workers (79.8 and 282.9). The most frequent injury types were “struck by/against” (35.6%) and “work-related musculoskeletal disorders (WMSDs)” (19.5%). High risk industries included agriculture, construction, and manufacturing for both genders combined. For female young workers, the highest risk industry was healthcare. Conclusions: This study demonstrated the added value of non-disabling WC claims data. Using both disabling and non-disabling data and PI method, agriculture, construction, manufacturing and healthcare industries were identified as priority workplaces to prevent common and costly injuries among Oregon young workers. Practical Applications: While the industries identified are considered hazardous for all workers, findings in this study can guide targeted research and prevention efforts specific to young workers. 相似文献