The existing deep learning-based Personal Protective Equipment (PPE) detectors can only detect limited types of PPE and their performance needs to be improved, particularly for their deployment on real construction sites. This paper introduces an approach to train and evaluate eight deep learning detectors, for real application purposes, based on You Only Look Once (YOLO) architectures for six classes, including helmets with four colours, person, and vest. Meanwhile, a dedicated high-quality dataset, CHV, consisting of 1330 images, is constructed by considering real construction site background, different gestures, varied angles and distances, and multi PPE classes. The comparison result among the eight models shows that YOLO v5x has the best mAP (86.55%), and YOLO v5s has the fastest speed (52 FPS) on GPU. The detection accuracy of helmet classes on blurred faces decreases by 7%, while there is no effect on other person and vest classes. And the proposed detectors trained on the CHV dataset have a superior performance compared to other deep learning approaches on the same datasets. The novel multiclass CHV dataset is open for public use.

We report the distribution and habitat selection by the Red-crowned Crane Grus japonensis in winter in the Yancheng Biosphere Reserve, China. Including original wetlands and artificial habitats, six types of habitat are used by the species: saltworks (salinas), fish ponds, reed beds, Wormwood Artemisia halodendron beaches, tidal grasslands and wheat fields. We compared the habitat availability with habitat use in each type.In winter, Red-crowned Crane preferentially used tidal grasslands and fish ponds. Saltworks, Wormwood beaches and wheat fields were avoided. The distribution of Red-crowned Crane in different types of habitat changed with the distribution of freshwater and with human activities.The Red-crowned Crane Grus japonensis is one of the most vulnerable bird species in the world (Collar et al.

No abstract