JP2907641B2 - Work area detection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a color image pickup means for picking up an image of a work area in a predetermined range, and a work object on the work ground based on color image information obtained by the color image pickup means. The present invention relates to a work area detection device provided with area extraction means for extracting a corresponding area.

[0002]

2. Description of the Related Art In the above-mentioned work area detecting apparatus, for example, a seedling as a work target is planted in a field as a work target land by a rice planting machine, and a planted work land where the seedlings are planted and an unplanted plant adjacent thereto are planted. A work place is detected.
Then, based on this area detection information, for example, the boundary between the planted work site and the unplanted work site is determined, and the steering control is performed so that the rice transplanter will automatically travel along the determined boundary. Therefore, color signal components (usually three primary color signals of red, green and blue) included in the color image information of the seedling by a color video camera as a color imaging means and a color image such as a mud surface or a water surface other than the seedling. Paying attention to the difference from the color signal component included in the information, an area corresponding to the seedling is extracted from the color image information by a predetermined arithmetic processing, and the side where the area corresponding to the seedling is extracted is subjected to the above-described planting operation. While detecting as a land, the side where the area | region corresponding to a seedling is not extracted is detected as said unplanted work land.

By the way, the ratio of the color signal components in the light irradiated on the field, usually natural light such as sunlight, fluctuates due to a change in weather (for example, from fine weather to cloudy).
Due to this variation, the ratio of the color signal components included in the color image information of the seedlings, mud surface, and the like imaged under the irradiation light is also adjusted to a state in which appropriate color reproduction is possible (for example, under sunlight in fine weather). ) Varies from the appropriate signal component ratio in the color image information. Therefore, if the area is extracted based on the color image information in which the ratio of the color signal components fluctuates, incorrect area information may be obtained. Therefore,
In order to avoid this, for example, in the case of irradiation light in which the ratio of the red signal component to the green signal component is relatively large,
By performing color balance correction such that the signal component of the color image information corresponding to the red signal is made relatively small with respect to the green signal component, the ratio of the color signal component in the color image information is calculated as the ratio of the color signal component of the irradiation light. We maintain the ratio appropriately regardless of the fluctuation of the ratio.

However, conventionally, when the weather changes at the start of the work and during the work, each time, the worker uses a white reference body (for example, a transparent white resin plate) under the irradiation light at that time.
The color balance correction process is performed by, for example, operating a switch while the camera is in front of the lens of the camera.

[0005]

However, in the above-mentioned prior art, it is necessary for the operator to manually perform the color balance correction operation, which is troublesome, and when the weather changes during the work, etc. It is difficult to judge the necessity of the correction operation, so that there is a problem that the operation is easily forgotten. If the correction is not performed despite the necessity of the correction operation, the accuracy of the area detection is reduced. Therefore, for example, the difference between the planted side and the unplanted side determined based on this area information is determined. The steering control along the boundary is not executed in an appropriate steering state.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and an object of the present invention is to automatically perform color balance correction on color image information without troublesome work of an operator. is there.

[0007]

A feature of the work area detecting apparatus according to the present invention is that a color signal ratio detecting means for detecting a ratio of a color signal component to a set proper signal component ratio in light illuminating the work area. And color balance correction means for performing color balance correction based on the information of the color signal ratio detection means, such that the color image information corresponding to the color signal component having the large ratio has a smaller output as the color image information, The area extracting means,
It is characterized in that the extraction processing is performed based on the color image information on which color balance correction has been performed by the color balance correction means.

[0008]

According to the characteristic configuration of the present invention, the setting appropriate signal component ratio (appropriate color reproduction) of the color signal components (three primary color signals of red, green, and blue) in the light irradiated to the work target site such as the field. (Corresponding to the signal component ratio of the color image information in a state in which it is possible) is detected, and among the color signal components included in the color image information obtained by imaging the work object such as a seedling on the work ground, For a signal component having a large ratio with respect to the set proper signal component ratio, the output is made smaller than that of a signal component having a small ratio. On the other hand, for a signal component having a small ratio, the output is made smaller than that of a signal component having a large ratio. Be enlarged. That is, for example, in the case of irradiation light in which the ratio of the red signal component is large and the ratio of the green signal component is small compared to the setting appropriate signal component ratio, the color signal component corresponding to the red signal is compared with the green signal component. Color balance correction is performed to make it relatively small, so that even if the ratio of the color signal components in the illuminating light fluctuates from the set proper signal component ratio, signal processing is performed to correct the fluctuation and the proper color Color image information that can be reproduced is obtained. Therefore, based on the appropriate color image information, a region corresponding to a work target such as a seedling can be accurately extracted.

[0009]

As described above, according to the present invention, even when the ratio of the color signal components of the light illuminating the work target area fluctuates from the set proper signal component ratio, the color balance is appropriately and automatically corrected. Therefore, it is possible to obtain a work area detection device excellent in operability and reliability without troublesome work of an operator and without causing a malfunction of the area detection due to forgetting the operation.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment in which the present invention is applied to a seedling detecting device in a rice planting machine will be described below with reference to the drawings.

As shown in FIGS. 4 and 5, a seedling planting device 2 is provided at the rear of a work vehicle V having a pair of left and right front wheels 1F and a pair of left and right rear wheels 1R as steering wheels so as to be able to move up and down. In the seedling planting device 2, a plurality of planted seedlings T as work objects arranged in a row are planted in a field M as a work target site to form a planted work site M2. A color video camera S1 as a color imaging means for imaging a field M in a predetermined range on the front side of the vehicle body
Are provided on the front side of the work vehicle V.

The mounting structure of the color video camera S1 will be described. The front end of the support member 4 protruding laterally outward of the work vehicle V is located adjacent to the work vehicle V laterally outward of the vehicle body. The photographed seedlings Tn to be picked up are taken obliquely from above in the vehicle traveling direction.
That is, in a state where the work vehicle V is properly aligned with the row of the plurality of seeded seedlings T arranged in the vehicle traveling direction,
Planted seedlings T on the planted work site M2 adjacent to the unplanted work site M1
The line segment L corresponding to n corresponds to the running reference line La passing through the center of the field of view of the color video camera S1 in the front-rear direction (see FIG. 4).

In order for the working vehicle V to sequentially travel through a plurality of field steps set so as to be arranged on the field M and to plant the seedlings T over the entire field M, each field step is performed. Then, the steering control is performed based on the image information of the color video camera S1 so that the work vehicle V automatically runs along the line segment L corresponding to the planted seedling Tn.
However, as the end of one field stroke is reached, one end is moved from the end of the field stroke to the beginning of the next field stroke.
It is automatically controlled to turn by 80 degrees and move.

Therefore, normally, the traveling direction of the work vehicle V with respect to the field M is changed every time the vehicle travels one stroke, and the position of the planted seedlings T with respect to the work vehicle V is left and right reversed. The color video camera S1 is a work vehicle V
One camera is provided for each of the left and right, and the camera to be used is switched left and right for each stroke. Incidentally, in FIG. 4, since the position of the planted seedlings T is on the right side of the work vehicle V, the right color video camera S1 is used.

The construction of the working vehicle V will be described.
As shown in FIG. 1, after the output of the engine E is shifted by the transmission 5, the pair of left and right front wheels 1F and the pair of left and right rear wheels 1R are provided via differential devices 12F and 12R provided on the front and rear axles of the vehicle. , Respectively, to form a so-called four-wheel drive type. Then, the so shifting operation state by the shift device 5 is operated state corresponding to the set travel speed set in advance, the shifting state detection potentiometer R ₃ provided, the detection information of the shifting state detecting potentiometer R ₃ Is configured to drive the shift electric motor 6 based on the

[0016] Also, the pair of left and right front wheels 1F is configured to be powered steering operation by a hydraulic cylinder 7F, so that the detected steering angle by the steering angle detecting potentiometer R ₁ which is linked to the steering operation becomes the target steering angle In addition, it is configured to drive an electromagnetically operated control valve 8F for operating the hydraulic cylinder 7F. Therefore, the work vehicle V is steered in a two-wheel steering mode in which only the front wheels 1F are turned, and is automatically steered based on the imaging information of the color video camera S1.
Also, when the work vehicle V for completing one field stroke and moving to the next field stroke is turned, the IF is turned by steering operation toward the next field stroke.
In FIG. 1, S2 is a distance sensor for detecting a traveling distance based on the output speed of the transmission 5, and S3.
Is a geomagnetic sensor based on a fluxgate system for detecting the angle of the traveling direction of the work vehicle V (see FIGS. 4 and 5).

Next, as shown in FIG. 1 to FIG. 3, based on an NTSC color video signal as imaging information input from the pair of left and right color video cameras S1,
The unplanted work site M1 and the already-planted work site M2 in the vehicle width direction.
The configuration of the boundary detecting device 101 for detecting the line segment L corresponding to the planting boundary with the above will be described.

The boundary detecting device 101 has an NTSC which has passed through a camera switching circuit 13 for selectively switching the color video signals from the pair of left and right color video cameras S1.
A NTSC decoder 3 for separating a color video signal of a format into a vertical synchronizing signal VD, a horizontal synchronizing signal HD, and a green signal Gi, a blue signal Bi and a red signal Ri; and the green signal Gi, The blue signal Bi and the red signal Ri are converted into ratio information B from the color signal ratio detection unit 60.
a color balance correction unit 70 for correcting the color balance based on c and Rc, and a green signal G, a blue signal B and a red signal R corrected by the color balance correction unit 70 by an arithmetic expression (3G-2B-R). A color operation unit 20 that operates in the state of an analog signal, a binarization processing unit 30 that extracts an area Ta corresponding to the planted seedling T based on an output signal of the color operation unit 20 based on a set threshold value Cref, The binarized image information F1 (FIG. 7 (b)) corresponding to the planted seedlings T extracted by the binarization processing unit 30 is converted into 32 × 32
An image memory 9 for storing as image information composed of one pixel / one screen and a representative point P of each region Ta of the binarized image information F1 stored in the image memory 9 are connected after connecting these representative points P. The line segment L (FIG. 7 (c)) is linearly approximated by a Hough transform, and the straight line L on the imaging surface is converted into a straight line L on the ground surface, and the inclination に 対 す る with respect to the running reference line La and the width 方向A linear calculation unit 40 for outputting information on the position δ (FIG. 9), a control unit 50 for controlling the operation of each unit, and a monitor 1 for displaying a captured image and an output of each unit.
0 and a CRT controller 11 that receives the vertical synchronizing signal VD and the horizontal synchronizing signal HD and generates various control signals for synchronizing the operations of the respective units.
Note that H is a travel control device using a microcomputer for controlling travel based on the information of the boundary detection device 101.

Next, the configurations of the color signal ratio detecting section 60, the color balance correcting section 70, the color calculating section 20, and the binarizing section 30 will be described in detail. As shown in FIG. 3, the color signal ratio detection unit 60 converts the light (normally, sunlight) irradiated onto the field M into three filters corresponding to the three primary colors of green G, blue B, and red R, respectively. 61G, 61
B, after passing through 61R, each filter 61G, 61B,
The passing light from 61R is converted to a photodiode 62 such as Cds.
The voltage signals are respectively converted into voltage signals. Further, each voltage signal is amplified by the amplifier 63 at the same amplification factor, and then input to the color signal ratio calculator 64. Then, the color signal ratio calculator 64 calculates the signal component ratios Eb and Er of the blue signal B and the red signal R when the magnitude of the signal component is set to 1 with respect to the green signal G, for example, during the daytime in fine weather. , A ratio Bc (= Eb / Eb ′) representing the ratio of change to the set proper signal component ratios Eb ′ and Er ′ obtained in a state where sunlight is irradiated, and a ratio representing the red signal R. Rc (= Er / Er ′) is calculated. As described above, the color signal ratio detection unit 60 corresponds to a color signal ratio detection unit that detects the ratios Rc and Bc of the color signal components in the light applied to the field M to the set proper signal component ratio. The photodetector 65, which supports and fixes the three filters 61G, 61B, 61R and the corresponding photodiodes 62 in a predetermined arrangement, is located at the front position of the body V with its light receiving surface facing upward. (See FIGS. 4 and 5).

The color balance corrector 70 includes a green signal Gi and a blue signal Bi from the NTSC decoder 3.
And three amplifiers 71G for amplifying each of the red signal Ri,
71B and 71R are provided, and the three amplifiers 71G and 71R are provided.
Among the 71B and 71R, the amplifier 71G for amplifying the green signal Gi is amplified at a predetermined amplification rate, whereas the amplifier 71B for amplifying the blue signal Bi and the amplifier 71R for amplifying the red signal Ri are The amplification factor is changed according to the color signal component ratio information Bc and Rc output from the color signal ratio calculator 64, respectively. Specifically, when the ratio Bc, Rc is 1, the gain is the same as the amplification factor of the amplifier 71G of the green signal Gi. As the ratio signal Bc, Rc is larger than 1, the amplifier 71G of the green signal Gi is increased. Becomes smaller than the amplification factor. For example, if the ratio signals Bc and Rc become 2, the amplification ratio becomes の of the amplification ratio of the green signal Gi. As described above, the color balance correction unit 70 determines the ratios Rc, B based on the information of the color signal ratio detection unit 60.
The color image information R, G, B corresponding to a color signal component having a large c corresponds to a color balance correction means for performing a color balance correction such that the output is reduced.

The color calculating section 20 operates in synchronization with the vertical synchronizing signal VD and the horizontal synchronizing signal HD.
While the operation is controlled by the timing controller 21, the green signal G, blue signal B, and red signal R, which have been subjected to the color balance correction and output from the color balance correction unit 70, are calculated by the adder / subtracter 22 using the arithmetic expression (3G-2
BR), and the output signal is amplified to a predetermined level by the video amplifier 23 whose amplification degree is set by the gain setting resistor Rg. Next, in the binarization processing unit 30, the amplified video signal is compared with the set threshold value Cref output from the threshold value generator 31 by the comparator 32, and the captured image information shown in FIG. 2 above
It is converted into valued image information F1. As described above, the color operation unit 20 and the binarization processing unit 30 use the color image information R, G, B from the pair of left and right color video cameras S1.
Based on the above, an area extracting means 100 for extracting an area Ta corresponding to the already planted seedlings T on the field M is configured, and further, the area extracting means 100 is subjected to color balance correction by the color balance correction unit 70. The extraction processing of the area Ta is performed based on the color image information R, G, and B.

To explain the above-mentioned extraction processing, the intensity of the green signal G, the blue signal B and the red signal R, which are the captured image information, is reflected in the portion where the seedlings T exist, the portion corresponding to the mud surface, and the natural light is reflected. Considering each of the water surface portions, the intensity of the green signal G is large, and the intensity of the blue signal B and the intensity of the red signal R are small in the portion where the seedlings T exist. Also, in the portion corresponding to the mud surface, the green signal G,
The intensity of each of the blue signal B and the red signal R becomes small.
Further, in the water surface portion, the intensity of each of the green signal G, the blue signal B, and the red signal R becomes large. Therefore, the influence of the image information corresponding to the mud surface and the light reflected on the water surface is removed based on the magnitude of the signal level processed by the above-mentioned arithmetic expression (3G-2B-R). That is, by extracting and binarizing a portion where the signal level is equal to or higher than the set threshold value Cref, the region Ta corresponding to the seedling T is extracted.
Information can be obtained in real time. The set threshold value Cref is appropriately changed and adjusted to an appropriate value depending on conditions such as the color state of the seedling T and the surrounding brightness.

Further, the traveling control device H controls the steering so that the work vehicle V automatically travels along the planting boundary L in each of the plurality of field strokes based on the detection information of the boundary detecting device 101. In addition, as the work vehicle V reaches the end of one field trip, a turn control for moving the work vehicle V to the beginning of the next field trip based on a turn pattern stored in advance is performed. Have been.

Next, based on the flowchart shown in FIG. 6, the configuration of each part will be described in detail while describing the boundary detection processing by the boundary detection device 101.

In the boundary detection processing, the color video camera S1 performs an imaging process every time the work vehicle V travels a set distance or at a set time, and the captured image information obtained by this imaging process is After the color balance correction is performed as described above, an area Ta corresponding to the seedling T is extracted (see FIGS. 7A and 7B). Then, an area Tan adjacent to the unplanted work site M1 is extracted from the area Ta, and the nearest pixel to the stock source side is extracted as a representative point P in each of the areas Tan (see FIG. 7C). Based on these representative points P, the planting boundary L is obtained by linear approximation by Hough transform processing.

The Hough transform will be described with reference to FIG. 8, where the x-axis passing through the center (x = 16, y = 16) of the field of view of the color video camera S1 is used as a reference line in a polar coordinate system. A plurality of straight lines passing through the point P
0 to 180 with respect to the x-axis based on the following equation (i).
A gradient θ previously set in a plurality of steps in the range of degrees,
It is obtained as a combination with the origin, that is, the distance ρ from the center of the screen corresponding to the center of the imaging visual field. ρ = y · sinθ + x · cosθ (i)

Then, for all the representative points P, the frequency of each straight line corresponding to the combination of the parameters (ρ, θ) is counted until the value of the inclination θ set in the plurality of steps reaches 180 degrees. Is repeated for adding the two-dimensional histogram. When the counting of the frequency of the straight line with respect to all the representative points P is completed, the slope θ and the distance ρ, which are the maximum frequencies, are obtained from the value added to the two-dimensional histogram.
Is determined, and one straight line Lx having the maximum frequency is determined, and the straight line Lx is obtained as information obtained by linearly approximating a line segment corresponding to the planting boundary L on the imaging surface of the color video camera S1.

Next, as shown in FIG. 9, a straight line Lx on the image pickup plane is obtained by measuring the shape and size of the image pickup visual field A of the color video camera S1 on the ground surface measured in advance and the maximum frequency. Is converted into information on a straight line L on the ground surface based on the pixel positions a, b, and c on the imaging plane through which the straight line Lx passes. That is, the inclination に 対 す る with respect to the traveling reference line La passing in the front-rear direction at the center in the width direction of the imaging field of view A,
It is converted into information of a straight line L on the ground surface set as a value with the position δ in the width direction.

In other words, the length l ₀ of two sides at the front and rear positions (y = 0 and y = 32) of the imaging visual field A in a direction intersecting the straight line L corresponding to the planting boundary L
l ₃₂ , center of screen (pixel position where x = 16, y = 16)
, The length l ₁₆ of the imaging field of view A in the width direction and the distance h between the front and rear sides are actually measured in advance and stored in the travel control device H. Then, the x-coordinate of positions a and b (positions where y = 0 and y = 32) of pixels where the straight line Lx on the imaging plane intersects the x-axis corresponding to two sides at the front and rear positions of the imaging field of view A The value X of
_0, and X _32, and a value X ₁₆ in the x coordinate of the position c of pixels the straight line Lx intersects the x axis passing through the center of the screen, to be determined from the following (ii) expression obtained by modifying the formula (i) Become. Xi = (ρ−Yi · sin θ) / cos θ (ii) Here, 0, 16, and 32 are substituted for Yi, respectively.

Then, based on the coordinate values on the x-axis determined by the above equation (ii), the following formulas (iii) and (iv) are used to calculate the position δ in the lateral width direction with respect to the travel reference line La.
And the slope ψ, and the obtained values of the position δ and the slope ψ
It is calculated as the position information of the straight line L corresponding to the planting boundary L on the ground surface.

[0031]

(Equation 1)

Then, the work vehicle V is moved to the unplanted work place M.
In the steering control for automatically traveling along the planting boundary L between the planting work land M1 and the planting work site M2, the inclination に 対 す る of the linearly approximated planting boundary L with respect to the traveling reference line La and the position δ in the lateral width direction As described above, the steering operation is performed in a two-wheel steering system so that both are brought close to zero.

The steering control will be described from the values of the inclination ψ of the straight line L with respect to the traveling reference line La and the position δ in the lateral width direction and the value of the current steering angle φ of the front wheel 1F. , based on the following (vii) type, sets a target steering angle θf of the front wheel 1F, and the current steering angle φ is detected by the steering angle detecting potentiometer R ₁ for said front wheel target steering The control valve 8F of the front wheel hydraulic cylinder 7F is driven so as to be maintained within the set dead zone with respect to the direction angle θf. θf = K ₁ · δ + K ₂ · ψ + K ₃ · φ (vii) Note that K ₁ , K ₂ , and K ₃ are constants preset in accordance with the steering characteristics.

For example, when the front end of the ridge existing along the vehicle body width direction on the front side in the traveling direction comes to a predetermined position in the field of view of the color video camera S1, the work vehicle V Is detected, the planting operation by the seedling planting apparatus 2 is interrupted, and then the seedling is moved toward the beginning of the next field trip based on a previously stored turn pattern. Then, the control is shifted to the 180-degree turn control.

[Alternative Embodiment] In the above-described embodiment, the color video camera S1 is used as a color imaging means, and the green signal G, the blue signal B, and the red signal R are subjected to a predetermined arithmetic expression (3
G-2B-R), the signal level processed according to the set threshold value Cref is binarized to extract a region Ta corresponding to the seedling T in the field M. Is not limited to the above, and can be changed as appropriate. Alternatively, the area Ta may be extracted by binarizing the color difference signal GB obtained using the green signal G and the blue signal B among the three primary color signals R, G, and B based on the set threshold value Cref. The specific configuration of the area extracting means 100 can be variously changed. The signal format of the color video camera S1 is also N
The signal is not limited to the TSC method, and any signal that outputs a color signal such as a green signal G or a blue signal B may be used.

In the above embodiment, the color signal ratio detecting means 60 determines the signal component ratios Eb, Eb, of the blue signal B and the red signal R when the magnitude of the signal component is set to 1 with respect to the green signal G. Er is the set appropriate signal component ratio Eb ′,
The ratio Bc (= Eb / Eb ') representing the ratio changed from Er' for the blue signal B and the ratio Rc (= Er / Er ') representing the red signal R are calculated. However, the blue signal B or the red signal R may be used as a reference. The above-mentioned appropriate signal component ratios Eb ′ and Er ′ do not necessarily need to be set in the daylight sunlight irradiating state in fine weather. For example, when the signal component ratio of each of the color signals B, G and R is natural light such as sunlight. Alternatively, the irradiation may be performed in a state where light such as a lamp known to be used for lighting is applied. Further, the specific configuration of the optical system and the like is not limited to that of the above-described embodiment. For example, the light passing through the rotating three primary color filters may be received by one photodetector, or the photodetector may be a photodetector. The specific configuration of each part can be variously changed, such as using a phototransistor or a photoelectric tube in addition to the diode.

In the above-described embodiment, the color balance correction means 70 uses the blue signal B and the red signal to change the amplification factor according to the ratio signals Bc and Rc of the color signal components output from the color signal ratio detection means 60. When the ratio signals Bc and Rc of the respective signals R become 2 (or 0.5), for example, the amplification ratio is changed in a proportional relationship so that the amplification ratio becomes 1/2 (or 2 times) the amplification ratio for the green signal G. However, the change rate is not necessarily required to be changed in such a proportional relationship. For example, the change rate of the amplification rate may be smaller than the change rate of the ratio signals Bc and Rc. Also, regarding the specific configuration of the circuit and the like, instead of using three amplifiers as in the above embodiment, for example, the amplifier 71 of the green signal G is used.
The specific configuration can be variously changed, such as omitting G and using only two amplifiers, or using an attenuator instead of an amplifier to change the attenuation factor.

Further, in the above embodiment, the present invention is applied to the case where the planting boundary L between the planted work area and the unplanted work area in which the seedlings T as the work objects are planted in the field M as the work object area by the rice transplanter. Although the case where the detected information is used as the steering control information for automatically traveling along the planting boundary L has been described as an example, the present invention is also applicable to a lawn mower such as a lawn mower. It is also applicable to an apparatus for detecting an uncut turf region in order to obtain necessary information when cutting grass, and includes a work area and a type of work object, and a region corresponding to the detected work object. The specific configuration of each unit, such as the form of use of the information and the configuration of the traveling system of the aircraft, can be variously changed.

Incidentally, reference numerals are written in the claims for convenience of comparison with the drawings, but the present invention is not limited to the configuration of the attached drawings by the entry.

[Brief description of the drawings]

FIG. 1 is a block diagram of a control configuration.

FIG. 2 is a block diagram of a boundary detection device.

FIG. 3 is a block diagram of each unit for area extraction, color signal ratio detection, and color balance correction.

FIG. 4 is a schematic plan view of a rice planting machine.

FIG. 5 is a schematic side view of a rice transplanter.

FIG. 6 is a flowchart of a boundary detection process.

FIG. 7 is an explanatory diagram of a boundary detection process.

FIG. 8 is an explanatory diagram of a Hough transform.

FIG. 9 is an explanatory diagram showing a relationship between an aircraft traveling direction and an approximate straight line in an imaging field of view.

[Explanation of symbols]

 M Work target place S1 Imaging means R, G, B Color image information T Work target Ta area 100 Area extraction means Rc, Bc ratio 60 Color signal ratio detection means 70 Color balance correction means

──────────────────────────────────────────────────続 き Continuation of the front page (56) References JP-A 1-319878 (JP, A) JP-A 64-44694 (JP, A) JP-A 62-61509 (JP, A) (58) Field (Int.Cl. ⁶ , DB name) G06T 1/00 A01B 69/00 303 H04N 9/73

Claims (1)

(57) [Claims] 1. A color imaging means (S1) for imaging a work area (M) in a predetermined range, and color image information (R, G, B) by the color imaging means (S1). Area extracting means (100) for extracting an area (Ta) corresponding to the work object (T) on the work place (M)
And a ratio (Rc, B) of a color signal component to a set proper signal component ratio in light irradiated on the work target place (M).
c) based on the information of the color signal ratio detecting means (60) for detecting the color signal ratio detecting means (60)
Color balance correction means (70) for performing color balance correction such that the output of the color image information (R, G, B) corresponding to the color signal component having the larger ratio (Rc, Bc) is reduced. The area extracting means (100) is configured to perform the extraction processing based on the color image information (R, G, B) on which the color balance has been corrected by the color balance correcting means (70). Work area detection device.