Improved Method for Estimating Number of People Based on Convolution Neural Network

Fig. 3. Original images and visual density maps. (a) Image 1; (b) density map of image 1; (c) image 2; (d) density map of image 2; (e) color-density scale

Download full size

Fig. 4. Original images and estimated crowd density maps. (a) Image 1 with truth value of 36; (b) image 1 with estimation value of 31.5; (c) image 2 with truth value of 22; (d) image 2 with estimation value of 21.7

Download full size

Fig. 5. Comparison of density maps obtained by single-row network and combined network. (a) Image 1; (b) density map of image 1 by shallow network; (c) density map of image 1 by deep network; (d) density map of image 1 by DASCNN; (e) image 2; (f) density map of image 2 by shallow network; (g) density map of image 2 by deep network; (h) density map of image 2 by DASCNN

Download full size

Fig. 6. Contrast of crowd density estimations. (a) Image 1; (b) density map predicted in Ref. [9]; (c) density map predicted by proposed method; (d) image 2; (e) density map predicted in Ref. [9]; (f) density map predicted by proposed method

Download full size

Table 1. Dataset information of CAUC-CROWD、UCF-CROWD、AHU-CROWD
View table
Table 1. Dataset information of CAUC-CROWD、UCF-CROWD、AHU-CROWD
Dataset Number of images Resolution /(pixel×pixel) Number of people
CAUC-CROWD 225 800×602 7-204
UCF-CROWD 50 Different 94-4543
AHU-CROWD 107 Different 58-2201

Table 2. Comparison of results by proposed method and other algorithms
View table
Table 2. Comparison of results by proposed method and other algorithms
Method MAE MSE
Method in Ref. [9] 6.53 9.43
Method in Ref. [4] 10.75 15.89
Deep network 6.82 10.71
Shallow network 8.34 11.83
DASCNN 4.49 5.65

Table 3. Comparison of results by proposed method and other algorithms
View table
Table 3. Comparison of results by proposed method and other algorithms
Method MAE MSE
Method in Ref. [17] 493.4 487.1
Method in Ref. [14] 419.5 541.6
Method in Ref. [8] 467.0 498.5
Method in Ref. [9] 452.5 -
DASCNN 412.5 523.5

Table 4. Experimental results of estimating number of people from AHU-CROWD
View table
Table 4. Experimental results of estimating number of people from AHU-CROWD
Method MAE RD
Method in Ref. [4] 207.4 0.578
Method in Ref. [17] 409.0 0.912
Method in Ref. [18] 395.4 0.864
DASCNN 150.3 0.384

Tools

Get Citation

Copy Citation Text

Hongying Zhang, Sainan Wang, Wenbo Hu. Improved Method for Estimating Number of People Based on Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121503

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites