Search

Aiming at the problems of crowd distribution, scale feature, and crowd feature extraction difficulties in exhibition centers, this paper proposes a crowd density estimation method using deep learning for passenger flow detection systems in exhibition centers. Firstly, based on the pixel difference symbol feature, the difference amplitude feature and gray feature of the central pixel are extracted to form the CLBP feature to obtain more crowd group description information. Secondly, use the LR activation function to add nonlinear factors to the convolution neural network (CNN) and use dense blocks derived from crowd density estimation to train the LR-CNN crowd density estimation model. Finally, experimental results show that the mean absolute error (MAE) and mean square error (MSE) of the proposed method in the UCF_CC_50 dataset are 325.6 and 369.4, respectively. Besides, MAE and MSE in part_A of the Shanghai Tech dataset are 213.5 and 247.1, respectively, and they in part_B are 85.3 and 99.7, respectively. The proposed method effectively improves the accuracy of crowd density estimation in exhibition centers. [ABSTRACT FROM AUTHOR]

Conjunctivochalasis (Cch) is a very common ocular disorder, which can cause an unstable tear film and ocular discomfort. The study of vision-related quality of life (VR-QoL) in a community population with Cch can provide a better understanding of the impact of Cch on common people than objective clinical examinations alone. This cross-sectional comparative study enrolled 360 participants ≥40 years old living in Sanle Community, Shanghai. In the study, 198 subjects were diagnosed with Cch and 86 with dry eye syndrome (DES) without Cch. The remaining 76 subjects were normal controls. Socio-demographical data were collected, and Cch and related ocular symptoms and signs were evaluated. In addition, all participants were required to complete the Chinese version of the 25-item National Eye Institute Visual Functioning Questionnaire (NEI VFQ-25) and Ocular Surface Disease Index Questionnaire (OSDI). Main outcome measures include the comparison on the OSDI score and VFQ-25 score among the subgroups, and the correlation of these scores with the socio-demographical and clinical data. The results revealed that subjects with Cch had significantly decreased tear film stability even compared with those with DES (P = 0.001). The participants with either Cch or DES reported significantly higher OSDI scores and lower VFQ-25 composite scores than the normal controls (P<0.001 and 0.007 respectively). Further comparisons among the subgroups of Cch revealed that the following factors were associated with higher OSDI scores and lower VFQ-25 composite scores: nasal-side Cch, chalasis folds higher than tear meniscus height, punctal occlusion, or increased extent of chalasis on digital pressure. In conclusion, Cch was associated with an adverse impact on VR-QoL in a community population, and the impairment in VR-QoL had a significant correlation with disease severity and tear film abnormalities. [ABSTRACT FROM AUTHOR]