Machine vision system for identifying and sorting projectiles and other objects

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.

1 . A system for inspecting munitions, ordnance and other objects, comprising: 
 a feeder for receiving an object to be inspected;    a computer-vision system including multiple cameras for simultaneously imaging opposite sides of an object under inspection;    an image processor for analyzing the imaging and determining physical characteristics of an object; and    a sorter for diverting an object found by the image processor to be unacceptable.    
   
   
       2 . The system of  claim 1 , including one or more line-scan cameras.  
   
   
       3 . The system of  claim 1 , including: 
 one or more line-scan cameras; and    an image processor to recreate images of an object from the line data.    
   
   
       4 . The system of  claim 1 , including: 
 one or more line-scan cameras; and    wherein the image processor is operative to determine an object's speed and recreate images of an object from the line data based upon the speed.    
   
   
       5 . The system of  claim 1 , wherein the feeder includes a bore through which an operator loads ordnance.  
   
   
       6 . The system of  claim 1 , wherein the feeder is configured to receive belt ammunition.  
   
   
       7 . The system of  claim 1 , wherein the feeder is configured to receive bulk ammunition in a range of sizes.  
   
   
       8 . The system of  claim 1 , wherein: 
 the feeder is configured to receive loose objects in a range of sizes; and    further including a mechanism for forming a single line or column of objects for presentation to the computer-vision system.    
   
   
       9 . The system of  claim 1 , wherein: 
 the feeder is configured to receive loose objects in a range of sizes; and    further including a narrowing channel and restriction plates to form a single line or column of objects.    
   
   
       10 . The system of  claim 1 , wherein: 
 the feeder is configured to receive bulk ammunition in a range of calibers; and    further including a mechanism for forming a single line or column of bullets for presentation to the computer-vision system.    
   
   
       11 . The system of  claim 1 , wherein: 
 the feeder is configured to receive bulk ammunition in a range of calibers; and    further including a mechanism for separating bullets as a function of caliber.    
   
   
       12 . The system of  claim 1 , wherein the sorter includes a blow-off unit to divert objects found to be unacceptable.  
   
   
       13 . The system of  claim 1 , wherein the sorter is manually operated.  
   
   
       14 . The system of  claim 1 , wherein the image processor is operative to determine the color or hue of an object.  
   
   
       15 . The system of  claim 1 , wherein: 
 the image processor is operative to determine the color or hue of a bullet; and    identify the type of bullet based upon the color or hue.    
   
   
       16 . The system of  claim 1 , wherein the image processor is operative to recognize intensity.  
   
   
       17 . The system of  claim 1 , wherein the image processor is operative to: 
 recognize intensity; and determine if:    an ammunition cartridge is steel (gray) or brass, or    a bullet tip is silver or copper.    
   
   
       18 . The system of  claim 1 , wherein the image processor is operative to recognize alphanumerical characters, bar codes, or radio-frequency ID tags.  
   
   
       19 . The system of  claim 1 , wherein the image processor is operative to recognize imperfections associated with dents or corrosion.  
   
   
       20 . The system of  claim 1 , wherein the image processor is operative to recognize corrosion due to copper sulfate leakage.