Method and system of detecting foreign materials within an agricultural product stream

Patent metadata

Field	Value
Publication number	US-10197504-B2
Application number	US-201615289516-A
Country	US
Kind code	B2
Filing date	Oct 10, 2016
Priority date	Oct 10, 2016
Publication date	Feb 5, 2019
Grant date	Feb 5, 2019

Abstract

Methods and systems for detecting foreign material within a product stream in real-time, involve illuminating a portion of the agricultural product stream with light spanning a wavelength range including or within near-infrared and/or shortwave infrared wavelengths; scanning a line of the illuminated agricultural product stream to acquire a hyperspectral image of the line, the hyperspectral image of the line having a width of a single pixel; processing the hyperspectral image of the scanned line to obtain spectrum data for one or more pixels of the hyperspectral image of the scanned line; comparing the obtained spectrum data of the one or more pixels to predetermined spectrum data to determine whether the obtained spectrum data is indicative of foreign material within the scanned line of the agricultural product stream.

First claim

We claim:

1. A method of detecting foreign material within an agricultural product stream in real-time, the method comprising:
illuminating a portion of the agricultural product stream with light spanning a wavelength range including or within near-infrared and/or shortwave infrared wavelengths;
scanning a line of the illuminated agricultural product stream to acquire a hyperspectral image of the line, the hyperspectral image of the line having a width of a single pixel;
processing the hyperspectral image of the scanned line to obtain spectrum data for one or more pixels of the hyperspectral image of the scanned line; and
comparing the obtained spectrum data of the one or more pixels to predetermined spectrum data to determine whether the obtained spectrum data is indicative of foreign material within the scanned line of the agricultural product stream;
wherein multiple lines of agricultural product stream are individually scanned consecutively, and the consecutively scanned lines are separately processed in-real time; the method further comprising separately analyzing each consecutively scanned line to determine, for each scanned line, whether foreign material is detected; and mapping the foreign material when foreign material is detected in two or more consecutively scanned lines.

2. The method of claim 1 , wherein the scanned line of agricultural product stream is perpendicular to a direction in which the agricultural product stream is being moved.

3. The method of claim 1 , wherein the predetermined spectrum data is a calculated value based upon spectral data associated with one of the following materials: tobacco, foam, cardboard, plastic, foil, lubricant, or paper.

4. The method of claim 1 , further comprising a step of:
determining, based upon the comparing step, the location of foreign material in the product stream; or
determining, based upon the comparing step, that the scanned line of the agricultural product stream does not contain foreign material.

5. The method of claim 1 , wherein the processing step comprises calculating the Euclidean distance associated with one or more pixels of the hyperspectral image of the scanned line, wherein the Euclidean distance is calculated by the formula: d(p,q)=√{square root over (Σ i=1 n (q i −P i ) 2 )}, wherein p=( p 1 , p 2 . . ., p n ) and q=(q 1 ,q 2 . . ., q n ) and p and q are two points in Euclidean n-space.

6. The method of claim 1 , wherein the scanning step includes sensing a spectrum of light reflected, scattered, or emitted from the agricultural product stream with at least one sensor; wherein:
(a) the scanning is performed by a line-scan hyperspectral imaging device that includes the at least one sensor;
(b) the at least one sensor is an Indium Gallium Arsenide (InGaAs) sensor; and/or
(c) the at least one sensor is operable to sense light in a range of about 900 nm to 1700 nm or about 900 nm to 2500 nm.

7. The method of claim 1 , wherein:
(a) the scanning is performed by a line-scan hyperspectral imaging device wherein the hyperspectral imaging device operates in the range of about 900 nm to 1700 nm or about 900 nm to 2500 nm; and/or
(b) the illuminating is performed by a tungsten halogen light source.

8. The method of claim 1 , wherein the agricultural product stream is a continuously moving agricultural product stream and is conveyed on a conveyer belt operating at a speed of about 80-100 ft/min.

9. The method of claim 1 , wherein the processing step comprises:
calibrating the hyperspectral image of the scanned line by removing dark values of the hyperspectral image;
normalizing the hyperspectral image of the scanned line; and
smoothing the hyperspectral image of the scanned line to eliminate noise using median filtering.

10. The method of claim 1 , wherein the predetermined spectrum data is a threshold value associated with a single product material, a class of product materials, a single known foreign material, or a class of known foreign materials.

11. The method of claim 1 , further comprising:
generating an activation signal in response to determining that the scanned line of agricultural product stream comprises foreign material;
transmitting the activation signal to a removal system; and
removing the foreign material from the scanned line.

12. The method of claim 11 , wherein the foreign material is removed by a vacuum device and/or a forced fluid stream.

13. A non-transitory computer readable medium having instructions stored thereon, the instructions being configured to cause a processor to execute the steps of the method of claim 1 .

14. A method of detecting foreign material within an agricultural product stream in real-time, the method comprising:
illuminating a portion of the agricultural product stream with light spanning a wavelength range including or within near-infrared and/or shortwave infrared wavelengths;
scanning a line of the illuminated agricultural product stream to acquire a hyperspectral image of the line, the hyperspectral image of the line having a width of a single pixel;
processing the hyperspectral image of the scanned line to obtain spectrum data for one or more pixels of the hyperspectral image of the scanned line; and
comparing the obtained spectrum data of the one or more pixels to predetermined spectrum data to determine whether the obtained spectrum data is indicative of foreign material within the scanned line of the agricultural product stream;
wherein multiple lines of agricultural product stream are individually scanned consecutively, and the consecutively scanned lines are separately processed in-real time without constructing a hyperspectral image cube of the multiple lines.

15. A method of detecting foreign material within an agricultural product stream in real-time, the method comprising:
illuminating a portion of the agricultural product stream with light spanning a wavelength range including or within near-infrared and/or shortwave infrared wavelengths;
scanning a line of the illuminated agricultural product stream to acquire a hyperspectral image of the line, the hyperspectral image of the line having a width of a single pixel;
processing the hyperspectral image of the scanned line to obtain spectrum data for one or more pixels of the hyperspectral image of the scanned line; and
comparing the obtained spectrum data of the one or more pixels to predetermined spectrum data to determine whether the obtained spectrum data is indicative of foreign material within the scanned line of the agricultural product stream;
wherein the predetermined spectrum data is a threshold value associated with a single product material, a class of product materials, a single known foreign material, or a class of known foreign materials, and the threshold value is determined by a method comprising:
illuminating the product material, a class of product materials, a known foreign material, and/or a class of known foreign materials with light spanning a wavelength range including near-infrared and/or shortwave infrared wavelengths;
separately scanning the product material, the class of product materials, the known foreign material, and/or the class of known foreign materials to acquire hyperspectral reflectance image data for at least one of the respective product material, the class of product materials, the known foreign material, or the class of known foreign materials;
calculating, for at least one of the respective product material, the class of product materials, the known foreign material, or the class of known foreign materials, a mean value of reflectance intensity; and
based upon the o

Assignees

• Altria Client Services Llc

Inventors

• Sahu Amrita
• Dante Henry M
• Morris Jerry W

Classifications

• G01N2021/8592

  Grain or other flowing solid samples · CPC title

• G01N2021/8466

  Investigation of vegetal material, e.g. leaves, plants, fruits · CPC title

• G01N2021/845

  Objects on a conveyor · CPC title

• G01N2201/10

  Scanning · CPC title

• G01N2201/127

  Calibration; base line adjustment; drift compensation · CPC title