System and method for identifying arthropods in color-digital image information

• US 8,139,858 B1
• Filed: 03/29/2011
• Issued: 03/20/2012
• Est. Priority Date: 06/13/2003
• Status: Active Grant

• Current Assignee: Fernando Agudelo-Silva, Val R. Landwehr
• Original Assignee: Fernando Agudelo-Silva, Val R. Landwehr
• Inventors: Landwehr, Val R., Agudelo-Silva, Fernando
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US13/075,143
• Time in Patent Office: 357 Days
• Field of Search: 382/110, 382/162, 382/224, 382/254, 382/165, 382/168, 382/170, 382/173
• US Class Current: 382/170
• CPC Class Codes: A01M 1/026 combined with devices for monitoring insect presence, e.g. termites bait stations A01M1/2005; detecting other animals in a given area A01M31/002
• CPC Class Codes: A01M 1/145 Attracting and catching insects using combined illumination or colours and adhesive surfaces
• CPC Class Codes: A01M 3/005 Manual suction tools for catching insects
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69

Abstract

A color-based imaging system and method for the detection and classification of insects and other arthropods are described, including devices for counting arthropods and providing taxonomic capabilities useful for pest-management. Some embodiments include an image sensor (for example, a digital color camera, scanner or a video camera) with optional illumination that communicates with a computer system. Some embodiments include a color scanner connected to a computer. Sampled arthropods are put on a scanner to be counted and identified. The computer captures images from the scanner, adjusts scanner settings, and processes the acquired images to detect and identify the arthropods. Other embodiments include a trapping device and a digital camera connected by cable or wireless communications to the computer. Some devices include a processor to do the detection and identification in the field, or the field system can send the images to a centralized host computer for detection and identification.

Claims

1. An apparatus for identifying arthropods in color-digital image information from a color digital camera system connected to a communications unit, wherein the camera system has a lens, wherein the camera system is configured to obtain a first image of substrate and an arthropod on the substrate and to form first color-digital image information from the first image, wherein the communications unit has an interface operable to communicate across an internet, wherein the communications unit is operatively coupled to the camera system and configured to receive the first color-digital image information from the camera system and to transmit a first signal across the internet, and wherein the first transmitted signal is based on the received first color-digital image information, the apparatus comprising:

a computer coupled to the internet that receives the first transmitted signal with the first color-digital image information;

a detector, coupled to the computer, that detects the arthropod in the first color-digital image information;

a histogram generator, in the computer, that is coupled to receive the first color-digital image information, and to generate a first object-image histogram of the first image based at least in part on the first color-digital image information, wherein the first object-image histogram of the first image has a plurality of bins, each one of the plurality of bins located on;

a row corresponding to a value of a first color-space dimension, and a column corresponding to a value of a second color-space dimension; and

a classifier, in the computer, that classifies the arthropod based on the first image-object histogram of the first image and provides a categorization identifier based on the classification.

2. The apparatus of claim 1, wherein the first color-digital image information includes hue information for the first color-space dimension and color-saturation information for the second color-space dimension.

3. The apparatus of claim 1,

wherein the camera system obtains a second image of the arthropod on the substrate, forms second color-digital image information from the second image-and transmits a second signal across the internet, wherein the second transmitted signal is based on the second color-digital image information,

wherein the computer further receives the second transmitted signal with the second color-digital image information,

wherein the detector detects the arthropod in the second color-digital image information,

wherein the histogram generator is coupled to receive the second color-digital image information, and to generate a second object-image histogram of the second image based at least in part on the second color-digital image information, and

wherein the classifier classifies the type of the arthropod also based on the second-object histogram information.

4. The apparatus of claim 1, wherein the substrate includes a sticky surface having a plurality of areas including a first area and a second area, each of the plurality of areas having a solid color, and wherein the solid color of the first area contrasts with the solid color of the second area in order to obtain images of insects having different colors that contrast with one of the solid colors.

5. The apparatus of claim 1, wherein the classifier includes a KNN (K^th-nearest neighbor) classifier.

6. The apparatus of claim 1,

wherein the camera system obtains a second image of the arthropod on the substrate, forms second color-digital image information from the second image-and transmits a second signal across the internet, wherein the second transmitted signal is based on the second color-digital image information,

wherein the computer further receives the second transmitted signal with the second color-digital image information,

wherein the detector detects the arthropod in the second color-digital image information,

wherein the histogram generator is coupled to receive the second color-digital image information, and to generate a second object-image histogram of the second image based at least in part on the second color-digital image information,

wherein the classifier classifies the type of the arthropod also based on the second-object histogram information,

wherein the first image is obtained using a source of front illumination light, and

wherein the second image is obtained using a source of side illumination light such that the first image has different lighting conditions than the second image.

7. A method for identifying arthropods in color-digital image information from a color digital camera system having a lens, wherein the camera system obtains a first image of a substrate and an arthropod on the substrate, forms first color-digital image information from the first image and transmits a first signal to a remote computer across an internet, wherein the first transmitted signal is based on the first color-digital image information, the method comprising:

receiving, from the internet and into the computer, the first transmitted signal with the first color-digital image information;

detecting, in the computer, the arthropod in the first color-digital image information;

generating, in the computer, first-object histogram information based at least in part on the first color-digital image information; and

classifying, in the computer, a type of the arthropod based on the first-object histogram information and generating a categorization identifier based on the classifying.

8. The method of claim 7, wherein the camera system obtains a second image of the arthropod on the substrate, forms second color-digital image information from the second image and transmits a second signal to the remote computer across the internet, wherein the second transmitted signal is based on the second color-digital image information, the method further comprising:

receiving, from the internet and into the computer, the second transmitted signal with the second color-digital image information;

detecting, in the computer, the arthropod in the second color-digital image information;

generating, in the computer, second-object histogram information based at least in part on the second color-digital image information; and

wherein the classifying of the type of the arthropod is also based on the second-object histogram information.

9. The method of claim 8, wherein the first and second images are selectively illuminated with different wavelengths of illumination light selected to enhance images of arthropods of interest such that the second color-digital image information includes different color information than the first color-digital image information.

10. The method of claim 8, wherein the first and second images are selectively illuminated with different wavelengths of illumination light selected to enhance images of arthropods of interest such that the second color-digital image information includes different fluorescence information than the first color-digital image information.

11. The method of claim 8, wherein the first and second images are selectively illuminated with different polarization-directions of illumination light selected to enhance images of arthropods of interest such that the second color-digital image information includes different polarization information than the first color-digital image information.

12. The method of claim 7, further comprising adding the categorization identifier to a database, the database including information on a date and a location associated with the categorization identifier.

13. The method of claim 7, further comprising applying a pest-control protocol based on one or more categorization identifiers of the database.

14. The method of claim 7, wherein the classifying includes KNN (K^th-nearest neighbor) classifying.

15. The method of claim 7, wherein the first object-image histogram has a plurality of bins, each one of the plurality of bins located on:

a row corresponding to a value of a first color-space dimension, and a column corresponding to a value of a second color-space dimension.

16. A non-transitory medium having instructions stored thereon for causing a suitably programmed remote data processor in a computer connected to an internet to execute a method for identifying an arthropod in color-digital image information, the method comprising:

receiving, from the internet and into the computer, first color-digital image information;

detecting, in the computer, the arthropod in the first color-digital image information;

generating, in the computer, a first-object histogram based at least in part on the first color-digital image information; and

classifying, in the computer, a type of the arthropod based on the first-object histogram and generating a categorization identifier based on the classifying.

17. The computer-readable medium of claim 16, further comprising instructions such that the classifying further includes KNN (K^th-nearest neighbor) classifying.

18. The computer-readable medium of claim 16, wherein the first object-image histogram has a plurality of bins, each one of the plurality of bins located on:

a row corresponding to a value of a first color-space dimension, and a column corresponding to a value of a second color-space dimension.

19. The computer-readable medium of claim 16, further comprising instructions such that the method further comprises adding the categorization identifier to a database in the computer, the database including information on a date and a location associated with the categorization identifier.

20. The computer-readable medium of claim 16, further comprising instructions such that the method further comprises:

receiving, from the internet and into the computer, second color-digital image information;

detecting, in the computer, the arthropod in the second color-digital image information;

generating, in the computer, second-object histogram information based at least in part on the second color-digital image information; and

wherein the classifying of the type of the arthropod is also based on the second-object histogram information.