Method and system for detecting and classifying objects in images, such as insects and other arthropods

• US 7,496,228 B2
• Filed: 05/03/2004
• Issued: 02/24/2009
• 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: Agudelo-Silva, Fernando, Landwehr, Val R.
• Primary Examiner(s): Tran; Phuoc
• Application Number:
  US10/838,928
• Publication Number:
  US 20050025357A1
• Time in Patent Office: 1,758 Days
• Field of Search: 382/110, 382/162, 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 comprising:

an input device coupled to receive a digital image; and

a detector, coupled to the input device, that detects an object in the image;

a histogram generator coupled to receive object image information from the detector, that generates a first object-image histogram based at least in part on image information of the detected object, 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; and

a classifier that classifies the object based on the first image-object histogram and provides a categorization identifier based on the classification.

2. The apparatus of claim 1, wherein the histogram generator uses color information to generate the first image-object histogram, including hue information for the first dimension and color-saturation information for the second dimension.

3. The apparatus of claim 1, wherein histogram generator generates the first image-object histogram having the first dimension that includes hue and the second dimension that includes color-saturation.

4. The apparatus of claim 1, wherein the detector uses color information to detect the object, including both hue information and color-saturation information.

5. The apparatus of claim 1, wherein the histogram generator uses color information based on calculations, from the red, green, blue (RGB) values of each of a plurality of pixels, of substantially:

CR=0.701×

RED+0.587×

GREEN+0.114×

BLUE,

CB=−

0.299×

RED+0.587×

GREEN+0.886×

BLUE,

SATURATION=SQUARE ROOT(CR SQUARED+CB SQUARED), and

HUE=ARCTAN(CR/CB).

6. An apparatus comprising:

an input device coupled to receive a digital image; and

a detector, coupled to the input device, that detects an object in the image;

a histogram generator, coupled to receive object image information from the detector, that generates object-image-histogram information based at least in part on image information of the detected object;

a classifier that classifies the object based on the object-image-histogram information and provides a categorization identifier based on the classification; and

a distinguisher that distinguishes a first arthropod in the detected object from a second item in the detected object, in digital images where the detected object includes the first arthropod at least partially overlapped with the second item, using image information selected from a group consisting of luminance, hue, color-saturation information and combinations thereof.

7. An apparatus comprising:

an input device coupled to receive a digital image; and

a detector, coupled to the input device, that detects an object in the image;

a histogram generator, coupled to receive object image information from the detector, that generates object-image-histogram information based at least in part on image information of the detected object;

a classifier that classifies the object based on the object-image-histogram information and provides a categorization identifier based on the classification; and

a imagable surface having at least one sticky area for capturing arthropods and having at least one colored area for calibrating colors of the image.

8. A machine-implemented method comprising:

acquiring a digital image;

detecting a first arthropod object in the image; and

generating first-object histogram information based at least in part on color information of the detected first object; and

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

9. The method of claim 8, wherein the color information used to generate the histogram includes hue and color-saturation information.

10. The method of claim 8, further comprising:

detecting a second object in the image, wherein the second object is at least partially overlapped with the first object;

distinguishing the first object from the second object using image information selected from a group consisting of luminance, hue, color-saturation information and combinations thereof.

11. The method of claim 8, wherein the first-object histogram information is generated based on hue and color-saturation information, and

wherein the categorization identifier includes a genus identification and a species identification.

12. The method of claim 8, wherein the acquiring of the image includes filtering light for the image to limit a spectral range of the light.

13. The method of claim 8, wherein the acquiring of the image includes filtering light for the image to limit a polarization of the light.

14. The method of claim 8, wherein the acquiring of the image includes providing a sticky substrate having first background area that has a first color that is darker than the first object and a second background area that has a second color that is lighter than the first object.

15. The method of claim 8, wherein the acquiring of the image includes providing a substrate having first area that has a first calibration color, and a second area that has a second calibration color that is different from the first calibration color.

16. The method of claim 8, further comprising:

distinguishing the first object from a background image using image information selected from a group consisting of hue information, color-saturation information and combinations thereof.

17. The method of claim 8, further comprising:

adding the categorization identifier to a database, the database including information on a date and a location associated with the categorization identifier.

18. The method of claim 8, further comprising:

applying a pest-control protocol based on one or more categorization identifiers of the database.

19. An apparatus comprising:

an input device coupled to receive a digital image;

means for detecting a first arthropod object in the image and distinguishing the first object from a background image using image information selected from a group consisting of luminance, hue, color-saturation information and combinations thereof; and

means for classifying the detected first arthropod object that includes generating a histogram having a plurality of independent dimensions including at least a first dimension and a second dimension.

20. The apparatus of claim 19, farther comprising:

means for detecting a second object in the image, wherein the second object is at least partially overlapped with the first object, and for distinguishing the first object from the second object using image information selected from a group consisting of luminance, hue, color-saturation information and combinations thereof.

21. The apparatus of claim 20, wherein the second object is not an arthropod object.

22. The apparatus of claim 19, further comprising

means for acquiring the image including a filter to limit a spectral range of the light and to limit a polarization of the light, and wherein the image information used to distinguish the first object from the background includes luminance, hue and color-saturation information.