Application of color spectrum hyperspectral camera to the detection of whiteness classification of ores in open pit mines

一、 Introduction
It is an important work to test ore whiteness classification in open pit mine, which has a decisive influence on the effective utilization and fine processing of mineral resources. Traditional detection methods mainly rely on manual operation, which is not only inefficient, but also susceptible to subjective factors. Therefore, it is very important to adopt advanced detection technology to improve the accuracy and efficiency of ore whiteness classification detection. This paper introduces the application of color spectrum hyperspectral camera in the detection of whiteness classification of ores in open pit mines.

二、Background
The customer needs to test the whiteness of mine ore in a large area, but the detection efficiency by manual or hand-held whiteness meter is low, and a more efficient detection method is urgently needed.

A 400-1000nm hyperspectral camera was used for this classification detection, and FS13, a product of Color Spectrum Technology (Zhejiang) Co., LTD., was used for related research. The spectral range is 400-1000nm, the wavelength resolution is better than 2.5nm, and up to 1200 spectral channels can be reached. The acquisition speed can reach 128FPS in the full spectrum, and the maximum after band selection is 3300Hz (support multi-region band selection).

三、 Laboratory testing
The reflectance of calcium carbonate with different whiteness at 400-1000nm was obtained after the four ores were placed on the transmission platform and tested with FS-13.

It can be seen from Figure 4 that the primary whiteness and secondary whiteness are similar. According to the overall waveform, the primary and secondary whiteness can be classified into one category, and the tertiary and quaternary distinctions are obvious. The four-stage whiteness slope is high, the three-stage whiteness slope is low, and the overall difference with the first-stage and second-stage is large, and it is easy to distinguish.

四、On-site detection
Shooting time: 15:00, November 07, 2023

Figure 5

Figure 5 shows the hyperspectral camera FS-23 set up on site and the bench for detection.

Figure 6

Technicians selected a piece of calcium carbonate with second-grade whiteness in FIG. 6 and photographed it about 50m away. After modeling, the band curve was calibrated to invert the ore in the figure.

Figure 7

FIG. 7 shows the field shooting map of secondary calcium carbonate calibration at 20m and the inversion effect map.

Figure 8

FIG. 8 shows the field shooting map of primary calcium carbonate calibration at 20m and the inversion effect map.

Figure 9

FIG. 9 shows the field shooting map of primary calcium carbonate calibration at 50m and the inversion effect map.

Figure 10

As shown in Figure 10, after the parameter value (similarity threshold value) is adjusted from 0.993 to 0.99 at 50m, the proportion of primary calcium carbonate in similar bands after reverse selection is greatly increased.

Figure 11

Figure 12

In FIG. 11 and FIG. 12, an adjustment threshold with whiteness of secondary calcium carbonate is selected 50m away for inversion effect.

五、Conclusion

1. Laboratory testing
The 400-1000nm hyperspectral camera FS-13+ platform can be used to detect the whiteness classification of calcium carbonate, which is completely feasible in terms of identification feasibility. At the same time, it is found that the reflectance difference between primary whiteness and secondary whiteness is very small, and only two small differences are found, as shown in the following figure:

2. On-site inspection
The portable hyperspectral camera FS-23 can be used to shoot the field situation and invert the specific position, mainly inverting the primary and secondary calcium carbonate. When the model threshold is adjusted, the accuracy is gradually improved, so the primary and secondary whiteness of this area can be inverted to the general area. The disadvantage is that only a single model is used, and the accuracy still has great room for improvement.

3. Uav hyperspectral detection
If it is necessary to detect the whiteness level of calcium carbonate in a large area and efficiently in the future, the UAV-based hyperspectral measurement system can be used for detection. The UAV-based hyperspectral measurement system has the characteristics of high efficiency and low power consumption, and can provide high stability spectral image acquisition.

The application of color spectrum hyperspectral camera in the whiteness classification of ores in open pit has achieved some success. Through the acquisition and analysis of the hyperspectral data of color spectrum, the accurate detection of ore whiteness is realized, the accuracy and efficiency of detection are improved, and the error of manual operation is reduced. It is believed that in the future, with the further development of technology, color spectrum hyperspectral cameras will also play a greater role in the field of whiteness classification detection of open-pit ores, and provide more powerful technical support for the effective use of mineral resources and fine processing.