Machine vision system for identifying and sorting projectiles and other objects

Patent metadata

Field	Value
Publication number	US-9424634-B2
Application number	US-201313834909-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Mar 4, 2004
Publication date	Aug 23, 2016
Grant date	Aug 23, 2016

Abstract

A machine vision system for automatically identifying and inspecting objects is disclosed, including composable vision-based recognition modules and a decision algorithm to perform the final determination on object type and quality. This vision system has been used to develop a Projectile Identification System and an Automated Tactical Ammunition Classification System. The technology can be used to create numerous other inspection and automated identification systems.

First claim

We claim:

1. A method of inspecting and sorting munitions, ordnance or other manufactured parts, comprising the steps of:
consecutively conveying parts along a path which extends through a plurality of inspection stations including a circumference vision station;
facilitating movement of the parts through the circumference vision station such that all sides of each part are at least temporarily visually unobstructed;
illuminating an exterior side surface of each part when the part is visually unobstructed to generate a plurality of side images of the parts;
processing the side images of the part to identify physical part characteristics or defects; and
sorting the parts in accordance with the part characteristics or defects.

2. The method of claim 1 , including the steps of:
directing parts identified as having an unacceptable defect to a defective part area; and
directing parts not identified as having an unacceptable defect to an acceptable part area.

3. The method of claim 1 , including the step of generating at least two opposing side images of a part.

4. The method of claim 1 , including the step of constructing a profile of a part based upon the multiple side images.

5. The method of claim 1 , including the steps of:
storing a plurality of object templates;
processing the side images to generate length and profile information; and
determining part type by comparing the length and profile information to the stored templates.

6. The method of claim 1 , including the steps of:
storing information relating to one or more known types of defects based on shape, material type, surface markings, letters or head stamps, or parts being unknown or having an uninspected status; and
processing the side images of each part to identify part characteristics or defects based upon the stored information.

7. The method of claim 1 , including the steps of directing parts into one or more corresponding bins based upon part type, color, coding, or quality.

8. The method of claim 1 , including the step of conveying a single, consecutive line or column of parts through a space having at least one continuous circumferential gap such that all sides of each object passing through the gap are visible for illumination and imaging.

9. The method of claim 1 , including the step of conveying a single, consecutive line or column of parts down a v-channel such that each part accelerates at a predictable rate, the v-channel having one or more gaps facilitating illumination, imaging and profile capture on all sides.

10. The method of claim 1 , wherein the side images of the part are acquired with line scan cameras or two-dimensional image sensors.

11. The method of claim 1 , wherein the parts are illuminated with uniform ring illumination.

12. The method of claim 1 , wherein the parts are illuminated with a strobe light.

13. The method of claim 1 , including the step of generating side images that show part tip type, a model numbers or a lot number.

14. The method of claim 1 , including the step of using one or more of the following to determine part type, material, lot or model number:
a) Barcode, machine-readable code or character recognition,
b) RFID,
c) Size profiling,
d) Shape analysis,
e) Hue or RBG color analysis, and
f) End marking identification.

15. The method of claim 1 , including inspection stations that detect defects using one or more of the following:
a) Eddy current analysis,
b) Ultrasound analysis,
c) Laser spectroscopy for defect detection,
d) Laser interferometry,
e) Size profiling,
f) Shape analysis,
g) Hue or RBG color analysis for corrosion detection,
h) Intensity analysis, and
i) Gradient feature detection.

16. The method of claim 1 , wherein:
the parts are rounds of ammunition; and
the method includes the step of using a tip color image of each round to locating tip and tip type coding.

17. The method of claim 1 , including the step of using barcode, RFID, or character recognition to determine part end markings, if any.

18. A system for inspecting and sorting munitions, ordnance or other manufactured parts, comprising:
a feeder for consecutively conveying parts along a path which extends through a plurality of inspection stations;
the inspection stations including a circumference vision station through which each part is at least temporarily visually unobstructed;
an illumination assembly to illuminate a plurality of annular, exterior side surfaces of a part when the part is visually unobstructed;
an imaging assembly to generate a plurality of side images of the part when illuminated;
a processor for processing the side images to identify part characteristics or defects; and
a sorter for sorting the parts in accordance with the part characteristics or defects.

19. The system of claim 18 , wherein the processor is operative to construct a profile of a part based upon the multiple side images.

20. The system of claim 18 , further including:
a memory for storing a plurality of object templates; and
wherein the processor is operative to determine part type by comparing the length and profile information to the stored templates.

21. The system of claim 18 , further including:
a memory for storing information relating to one or more known types of defects based on shape, material type, surface markings, letters or head stamps, or parts being unknown or having an uninspected status; and
wherein the processor is operative to identify part characteristics or defects based upon the stored information.

22. The system of claim 18 , wherein the sorter includes one or more corresponding bins to receive parts based upon part type, color, coding, or quality.

23. The system of claim 18 , wherein the feeder includes a conveyor for conveying a single, consecutive line or column of parts through a space having at least one continuous circumferential gap such that all sides of each object passing through the gap are visible for illumination and imaging.

24. The system of claim 18 , including a vchannel conveyor through which parts in a single, consecutive line accelerate at a predictable rate, the vchannel having one or more gaps facilitating illumination, imaging and profile capture on all sides.

25. The system of claim 18 , wherein the imaging assembly acquires side images of the part with line-scan cameras or two-dimensional image sensors.

26. The system of claim 18 , wherein the illumination assembly is based upon uniform ring or strobe illumination.

27. The system of claim 18 , wherein the processor is operative to process the side images to determine part tip type, model number or lot number.

28. The system of claim 18 , further including one or more of the following to determine part type, material, lot or model number:
a) Barcode, machine-readable code or character recognition,
b) RFID,
c) Size profiling,
d) Shape analysis,
e) Hue or RBG color analysis, and
f) End marking identification.

29. The system of claim 18 , further including one or more of the following to determine defects:
a) Eddy current analysis,
b) Ultrasound analysis,
c) Laser spectroscopy for defect detection,
d) Laser interferometry,
e) Size profiling,
f) Shape analysis,
g) Hue or RBG color analysis for corrosion detection,
h) Intensity analysis, and
i) Gradient feature detection.

Assignees

• Cybernet Systems Corp

Inventors

• Beach Glenn J
• Moody Gary
• Burkowski James
• Jacobus Charles J

Classifications

• G06T2207/30164

  Workpiece; Machine component · CPC title

• G01N21/952

  Inspecting the exterior surface of cylindrical bodies or wires (G01N21/956 takes precedence) · CPC title

• B07C5/34

  Sorting according to other particular properties {(material testing per se G01N; quality control G07C3/14)} · CPC title

• G06K2209/19

  Physics · mapped topic

• G06T7/0004 Primary

  Industrial image inspection · CPC title