Image analysis – Applications – Target tracking or detecting
Reexamination Certificate
1999-11-30
2004-01-13
Boudreau, Leo (Department: 2621)
Image analysis
Applications
Target tracking or detecting
C348S169000
Reexamination Certificate
active
06678394
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to obstacle detection in mobile systems, and more particularly to an automated system for observing objects an area near a mobile system.
BACKGROUND OF THE INVENTION
Vehicle collision avoidance requires detection of nearby objects. In many cases the obstacles can be avoided by automatically stopping the vehicle, changing direction, or warning the operator when dangerous circumstances are observed. A person or object located in or approaching the vehicle's path may create dangerous conditions. Other obstacles include mechanical objects, holes in a travel surface, road boundaries, low bridges, and other conditions that can harm the vehicle, its load, or its occupants. Since obstacles encountered as a vehicle travels have different surface characteristics (reflectance, density, etc), robust detection can require numerous simultaneous safeguards, increasing system costs, and reducing reliability and flexibility of the vehicle.
Sensor technologies can be generally divided into two categories: active and passive. Active sensors insert or emit something into the area under test, and measure the response, or changes. Most lasers, radar, and ultrasonic sensors typically fall within this category. Passive sensors typically do not emit things into an area, rather they typically remain stationary and are activated by objects engaging/contacting the sensor or transducer. Mechanical probes, switches and camera-based systems typically fall within this category. In many applications, active sensors cannot be used for one reason or another, and passive sensors may provide superior capabilities in such cases. For example, when vehicles are operating in the same area using active sensor technologies such as laser, radar, or ultrasonic, the sensory emissions from other vehicles can be misinterpreted by receivers as reflections from objects and cause dangerous confusion.
Mechanical switches, photo-optical sensors and other proximity or motion sensors are well known safety and security components used in obstacle detection. These types of protection have the general disadvantage of being very limited in ability to detect more than a simple presence or absence (or motion) of an object, person, or other obstacle. In addition, simple sensors are typically custom specified or designed for the particular vehicle and the area to be navigated based upon a limited set of hazards. Mechanical sensors, in particular, have the disadvantage of being activated by unidirectional touching, and they must often be specifically designed for that unique purpose. They cannot sense any other types of collision, nor sense objects approaching nearby, nor objects arriving from an unpredicted direction. For example, a sensor lever on the front of a vehicle, resting on the ground, can sense a hole or other drop-off, but only at the location of the sensor. At higher vehicle speeds, sensing may occur too late for taking evasive actions. Even complicated combinations of motion and touch sensors can offer only limited and inflexible obstacle detection for circumstances in which one type of obstacle in the area should be ignored, and another type should result in evasive actions.
Ultrasonic sensor technologies are also available, based upon emission and reception of sound energy at frequencies beyond human hearing range. Ultrasonic sensing depends upon the hardness or density of an object, i.e., its ability to reflect sound. This makes ultrasonic sensors practical in some limited cases. Most significantly, like many simple mechanical sensors, the disadvantages of ultrasonic sensors include that they produce only a binary result, i.e., whether or not the vehicle has approached too close to an obstacle. Similar problems exist for known passive infra-red sensors, which can only detect the binary presence or absence of an object radiating heat, or more precisely, a change in the heat profile within the viewed scene. Each of these types of sensor is also susceptible to interference by emissions from other systems operating in the same general area.
Proximity laser scanners (PLS) can also be used to detect obstacles within a defined area near the PLS sensor. These systems are also known as Laser Measurement Systems (LMS). The PLS technology uses a scanning laser beam and measures the time-of-flight for reflected light to determine the position of objects within the viewing field. A relatively large zone, e.g., 50 meter radius over 180 degrees, can be scanned and computationally divided into smaller zones for early evasive actions or for emergency stops. However, like many of the other sensor technologies, the scanning laser systems typically cannot distinguish between different sizes or characteristics of obstacles detected, making them unsuitable for many collision avoidance applications. Significantly, the scanning laser systems typically incorporate moving parts, e.g., for changing the angle of a mirror used to direct the laser beam. Such moving parts experience wear, require precision alignment, are extremely fragile and are thus unreliable under challenging ambient conditions. Also, the PLS cannot discriminate between multiple obstacles and a single obstacle in the same location. Nor can such systems detect the orientation and direction of the obstacle within the area being monitored. Thus, an object moving across the path of the vehicle might raise the same alarm as a fixed obstacle at the same location toward which the vehicle is moving, causing a false alarm in the PLS.
The use of radar systems for collision avoidance is well known in the art. For example, U.S. Pat. No. 4,403,220 issued Sep. 6, 1983 discloses a radar system for collision avoidance in marine ships and aircraft. The system uses oscillating radar antennas and detects Doppler shift (relative speed) and direction of returned radio frequency pulses, and is specifically adapted for avoiding collisions. Similarly, U.S. Pat. No. 4,072,945 issued Feb. 7, 1978 discloses a collision avoidance system for motor vehicles using radar. The major disadvantage of using microwave radar devices is that physical constraints on the maximum antenna size generally result in a system having a relatively large minimum beam width. Given a wide beam, e.g., three degrees, the scanned area at a reasonable distance is much too broad to provide a useful result with any precision. Therefore, rather than limiting the detection field to obstacles in front of the vehicle, such systems also detect nearby objects that present no threat to the vehicle, such as road signs, trees, and bridges, generating false alarms. Another disadvantage of radar-based systems is that they have trouble discriminating among radar signals that emanate from other nearby vehicles that are using similar equipment, and other ambient interference. Furthermore, the requirement for precision calibration of moving parts makes the systems inherently unreliable in the presence of hostile environmental conditions, thus increasing operating and maintenance costs. Ultrasonic ranging and detecting equipment has similar disadvantages, to an even larger extent than radar, thus limiting such solutions to detection of objects that are very close to the sensor.
A “laser radar” system, such as that disclosed in U.S. Pat. No. 5,529,138 issued Jun. 25, 1996, teaches the use of a laser beam system on a vehicle for detecting obstacles. The system uses directed laser beams and reflection sensors to sense the relative location and speed of obstacles, estimate the size of an obstacle, and its relative direction of movement. Coupled with a speedometer input, the system can also estimate the ground speed of the obstacle. There are several disadvantages of laser radar systems. One major disadvantage is that a laser radar system can only detect its own reflected signal (ignoring interference) which is, by its very nature, a narrow beam. Even with an array of multiple lasers, each unit can only detect reflections from the narrow area being scanned by the beam. Also, mechanical mirrors are used
Boudreau Leo
Cognex Technology and Investment Corporation
Lu Tom Y.
Michaelis Brian
LandOfFree
Obstacle detection system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Obstacle detection system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Obstacle detection system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3231231