KR102107298B1 - Image analysis apparatus and method - Google Patents

Abstract

The present invention relates to an image analysis apparatus and method, and performs machine learning by receiving an object pixel value, an object environment pixel value, and an object environment variable that is affected by the surrounding environment, detected from an infrared image of an object in an object learning population. It includes an infrared image learning unit, an infrared image receiving unit for receiving the corresponding infrared image of the target object, and an object classifying unit for extracting the object pixel value based on the learning content of the machine learning from the infrared image to classify the target object. .

Description

Image analysis device and method {IMAGE ANALYSIS APPARATUS AND METHOD}

The present invention relates to an image analysis technology, and more particularly, to an image analysis apparatus and method capable of classifying a target object based on an infrared image.

In general, a vehicle is provided with various convenience means to provide a stable and comfortable driving condition. In addition to the demand for convenience means, the demand for devices for vehicle safety is also increasing.

Vehicle safety devices include active safety devices such as Anti-Blocking System (ABS) devices, Electronic Controlled Suspension (ECS) devices, and Autonomous Emergency Braking (AEB) devices, and black boxes for vehicles to determine the cause of post-incident accidents. The same manual safety device may be included.

Among them, the autonomous emergency braking system measures the distance between the vehicle (or object) driving in front of the vehicle through a radar mounted on the vehicle, and recognizes the danger of collision when the distance between the host vehicle and the vehicle in front is closer than a certain distance. When the danger of collision is recognized, the vehicle is decelerated by automatically braking.

In addition, when the danger of collision is recognized, the autonomous emergency braking system notifies the driver of the collision danger with a warning sound and operates the braking device in a standby mode so that the driver can respond quickly to pedal operation. In order to improve the performance of the autonomous emergency braking, it is necessary to quickly and accurately determine whether an object in front of the vehicle is a pedestrian, a vehicle, or other objects.

Korean Registered Patent No. 10-1671993 (2016.10.27) relates to a vehicle safety system, a photodiode, collision prevention distance calculation module, speed setting module, vehicle control module, traffic signal light detection module, color display module, and surrounding monitoring module Including, the color detection module sets the color of the traffic light as a range, the color of a certain range detected by the color detection module is determined by one color, and the color display module is the video information obtained from the traffic light detection camera module Displays the traffic light color area, and the vehicle speed control module stops the user's vehicle and flashes the emergency light when the color of the traffic light detected by the color detection module is red and the distance between the traffic light and the user's vehicle is within a certain distance. And the distance between the object detected by the surrounding distance calculation module and the user's vehicle is within a certain range. Right Stops the user's vehicle and flashes the emergency light, and the peripheral distance calculation module searches for the entire screen by size using blocks on the image obtained from the surrounding surveillance camera module, learns by dividing it by the brightness difference of the areas, and then learns the AdaBoost algorithm. It is characterized in that it uses weighting, combines weak classifiers to generate a strong classifier, detects a pedestrian face in the image, and sends a warning message if the distance between the pedestrian and the user's vehicle is within a certain range when a pedestrian face is detected. Is done.

Korean Registered Patent No. 10-1611273 (2016.04.05) relates to a subject detection system and method using sequential infrared images, which are disposed in a vehicle and emit infrared rays according to a preset cycle, and are reflected back from the subject Image data including the infrared component of the coming infrared component and the infrared component of the headlight of another vehicle is obtained, but when the infrared lamp emits infrared rays, the infrared image reflected from the subject returns and the on-image including the infrared component of the headlight of another vehicle and infrared rays When the lamp does not emit infrared rays, it includes an infrared camera that acquires an off-image that includes infrared components of other vehicle headlights, and a subject recognition unit that analyzes image data to detect a region of the subject.

Korean Registered Patent No. 10-1671993 (2016.10.27) Korean Registered Patent No. 10-1611273 (2016.04.05)

One embodiment of the present invention is to provide an image analysis apparatus and method capable of classifying a target object based on an infrared image.

An embodiment of the present invention is to provide an image analysis apparatus and method capable of minimizing the error of misidentifying a target object by reducing factors caused by the surrounding environment of the target object in the infrared image.

According to an embodiment of the present invention, after extracting a pixel value of the target object itself using a deep learning algorithm from an infrared image, an image analysis device capable of improving the recognition rate of the target object by classifying the target object using the extracted pixel value And to provide a method.

Among the embodiments, the image analysis apparatus receives an object pixel value, an object environment pixel value, and an object environment variable affected by the surrounding environment from an infrared image of an object in the object learning population, and performs an machine-infrared image. It includes a learning unit, an infrared image receiving unit that receives a corresponding infrared image related to a target object, and an object classification unit that classifies the target object by extracting a corresponding object pixel value based on the learning content of the machine learning from the corresponding infrared image. .

The infrared image learning unit is characterized by performing machine learning by inputting the object pixel value, the object environment pixel value, and the object environment variable, and outputting weights and biases according to the surrounding environment.

The infrared image learning unit is characterized in that it performs machine learning according to [Mathematics] below.

[Mathematics]

은 상기 객체 픽셀 값, 상기

는 상기 객체 픽셀 값 및 상기 객체 환경 픽셀 값의 합, 상기 α는 상기 가중치, 상기 β는 상기 바이어스, 상기 γ는 상기 객체 환경 변수) (Here,

Is the object pixel value, the

Is the sum of the object pixel value and the object environment pixel value, the α is the weight, the β is the bias, and γ is the object environment variable)

The object classifying unit extracts the corresponding object pixel value from the infrared image of the target object by using the machine-trained weight and bias corresponding to the surrounding environment of the target object, and extracts the range and extraction of object pixel values for each preset object And classifying the target object based on the comparison between the corresponding object pixel values.

The object classifying unit extracts the object pixel value of the target object according to the following [Equation].

[Mathematics]

는 상기 타깃 객체의 상기 객체 픽셀 값, 상기

는 타깃 객체의 상기 객체 픽셀 값 및 상기 객체 환경 픽셀 값의 합, 상기 α'는 기계 학습된 상기 가중치, 상기 β'는 기계 학습된 상기 바이어스, 상기 γ는 상기 객체 환경 변수)(Here,

Is the object pixel value of the target object, the

Is the sum of the object pixel values of the target object and the object environment pixel values, the α 'is the machine-learned weight, the β' is the machine-learned bias, and the γ is the object environment variable)

The object pixel value and the object environment pixel value may be values corresponding to any one of an infrared signal, an apparent temperature, and an RGB value.

Among the embodiments, the image analysis method receives the object pixel value and the object environment pixel value detected from the infrared image of the object in the object learning population, and the object environment variable affected by the surrounding environment to machine-learn to the surrounding environment. Calculating a weight and a bias according to the method, receiving a corresponding infrared image related to a target object, and extracting a corresponding object pixel value from the corresponding infrared image using the calculated weight and bias, and extracting the corresponding object pixel value And classifying the target object using.

The classifying of the target object may include matching the extracted object pixel value to a range of object pixel values for each preset object.

The disclosed technology can have the following effects. However, since the specific embodiment does not mean to include all of the following effects or only the following effects, the scope of rights of the disclosed technology should not be understood as being limited thereby.

The image analysis apparatus and method according to an embodiment of the present invention may classify a target object based on an infrared image.

The image analysis apparatus and method according to an embodiment of the present invention can minimize errors caused by the target object by reducing factors caused by the surrounding environment of the target object in the infrared image.

An image analysis apparatus and method according to an embodiment of the present invention extracts a pixel value of a target object itself using a deep learning algorithm from an infrared image, and then classifies the target object using the extracted pixel value to determine the recognition rate of the target object. Can be improved.

1 is a diagram illustrating an image analysis system according to an embodiment of the present invention.
2 is a schematic diagram illustrating a pixel value incident to an infrared camera.
FIG. 3 is a block diagram illustrating the image analysis device in FIG. 1.
FIG. 4 is a flowchart illustrating an infrared image analysis method performed in the image analysis device of FIG. 1.
5 and 6 are diagrams illustrating a process of performing infrared image analysis by applying the image analysis device of FIG. 1 to an autonomous vehicle.

Since the description of the present invention is only an example for structural or functional description, the scope of the present invention should not be interpreted as being limited by the examples described in the text. That is, since the embodiments can be variously changed and have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing technical ideas. In addition, the purpose or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such an effect, and the scope of the present invention should not be understood as being limited thereby.

Meanwhile, the meaning of terms described in the present application should be understood as follows.

Terms such as "first" and "second" are for distinguishing one component from other components, and the scope of rights should not be limited by these terms. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When a component is said to be "connected" to another component, it may be understood that other components may exist directly in the middle, although other components may be directly connected. On the other hand, when a component is said to be "directly connected" to another component, it should be understood that no other component exists in the middle. On the other hand, other expressions describing the relationship between the components, that is, "between" and "immediately between" or "adjacent to" and "directly neighboring to" should be interpreted similarly.

Singular expressions are to be understood as including plural expressions unless the context clearly indicates otherwise, and terms such as “comprises” or “have” are used features, numbers, steps, actions, components, parts or the like. It is to be understood that a combination is intended to be present, and should not be understood as pre-excluding the presence or addition possibility of one or more other features or numbers, steps, operations, components, parts or combinations thereof.

In each step, the identification code (for example, a, b, c, etc.) is used for convenience of explanation. The identification code does not describe the order of each step, and each step clearly identifies a specific order in context. Unless stated, it may occur in a different order than specified. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer readable code on a computer readable recording medium, and the computer readable recording medium includes all kinds of recording devices in which data readable by a computer system is stored. . Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, and optical data storage devices. In addition, the computer-readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

All terms used herein have the same meaning as commonly understood by a person skilled in the art to which the present invention pertains, unless otherwise defined. The terms defined in the commonly used dictionary should be interpreted as being consistent with the meanings in the context of related technologies, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present application.

1 is a diagram illustrating an image analysis system according to an embodiment of the present invention, and FIG. 2 is a schematic diagram illustrating a pixel value incident to an infrared camera.

Referring to FIG. 1, the image analysis system 100 may include an infrared camera 110, an image analysis device 130, and a database 150. The infrared camera 110 photographs an infrared image of the target object.

The image analysis device 130 performs machine learning by using the object pixel value and the object environment pixel value and the object environment variable affected by the surrounding environment, which are detected from the infrared image of the object in the object learning population, and the machine learning result The target object is classified by extracting the object pixel value from the infrared image of the target object based on.

)은 아래의 [수학식 1]과 같이 표현될 수 있다.Here, the object learning population may include a number of objects necessary for machine learning, for example, people, cars, signs, traffic lights, and the like. The pixel value according to an embodiment of the present invention may be any one of an infrared signal, an apparent temperature, and an RGB value. Pixel value incident to the infrared camera 110 (

) Can be expressed as [Equation 1] below.

는 도 2에 도시된 바와 같이, 외부 광원(210)의 빛이 객체(230)의 표면에서 반사되는 픽셀 값(220),

은 객체(230) 자체에서 표면 온도에 의해 방사되는 픽셀 값(240),

는 객체(230)에 도달하지 않고 대기에서 산란되는 픽셀 값(250)이다.From here,

As illustrated in FIG. 2, the pixel value 220 in which the light of the external light source 210 is reflected from the surface of the object 230,

The pixel value 240 emitted by the surface temperature in the silver object 230 itself,

Is a pixel value 250 that is scattered in the atmosphere without reaching the object 230.

을 객체 픽셀 값이라 하고,

과

의 합을 객체 환경 픽셀 값이라 명칭 한다.That is, the pixel value detected through the infrared camera 110 includes not only the pixel value of the object itself, but also the pixel value due to the surrounding environment. Hereinafter, for convenience in explanation

Is called object pixel value,

and

The sum of is called the object environment pixel value.

The database 150 is a storage device capable of storing various information necessary to extract object environment variables according to the surrounding environment and geographical conditions of the target object. For example, in the database 150, the location of the sun, the direct sunlight component, the diffusion component, the atmospheric temperature, the wind direction, the wind speed, the humidity, the atmospheric pressure, etc., depending on the latitude, longitude, and time of the target object may be stored as object environment variables. You can. To this end, the database 150 may be connected to a weather station server providing weather information, a server (not shown) providing map information, or the like.

The database 150 may be composed of at least one independent sub-database storing information belonging to a specific range, and may be composed of an integrated database in which at least one independent sub-database is integrated into one.

When composed of at least one independent sub-database, each sub-database may be wirelessly connected through Bluetooth, WiFi, etc., and may exchange data with each other through a network. When configured as an integrated database, the database 150 may include a control unit that integrates each sub-database into one and manages data exchange and control flow between each other.

FIG. 3 is a block diagram illustrating the image analysis device in FIG. 1.

Referring to FIG. 3, the image analysis device 130 includes an infrared image learning unit 310, an infrared image receiving unit 330, an object classification unit 350, and a control unit 370. The infrared image learning unit 310 performs machine learning by receiving an object pixel value, an object environment pixel value, and an object environment variable affected by the surrounding environment, which are detected from the infrared image of the object in the object learning population.

More specifically, the infrared image learning unit 310 uses an artificial intelligence algorithm to learn weights and biases according to the surrounding environment and geographic conditions of the object. For example, the infrared image learning unit 310 may perform machine learning using a convolution neural network (CNN), which is a type of deep learning.

Deep learning technology is an artificial intelligence (AI) technology that allows a computer to think and learn like a person, allowing the machine to learn and solve complex nonlinear problems based on artificial neural network theory. Deep learning is a technique in which the computer learns a machine to discern objects by imitating the information processing method that distinguishes objects after the human brain finds patterns in numerous data.

In other words, deep learning is defined as a set of machine learning algorithms that attempt a high level of abstraction through a combination of several nonlinear transformation techniques, and is a field of machine learning that teaches a person's mindset to a computer in a large framework.

Methods for recognizing images and objects using deep learning include a convolutional neural network (CNN), a recurrent neural network (RNN), and a deep Q-network (DQN). Among them, the convolutional neural network (CNN) can recognize an object by using a pixel value of the image itself as a method specialized for 2D image processing.

Accordingly, the infrared image learning unit 310 according to an embodiment of the present invention uses the convolutional neural network (CNN) to object environment pixel values and object-only objects for the surrounding environment and geographic elements of the objects included in the infrared image. The pixel values are learned, and weights and biases according to the surrounding environment and geographic conditions of the object are calculated as the learning results.

Specifically, the infrared image learning unit 310 may include a learning process of inputting an object pixel value, an object environment pixel value, and an object environment variable, and outputting weights and biases according to the surrounding environment and geographic conditions of the object. have. For example, the infrared image learning unit 310 may perform learning as shown in [Equation 2] below.

은 객체 픽셀 값,

는 적외선 카메라(110)로 입사되는 총 픽셀 값, 즉 객체 픽셀 값 및 객체 환경 픽셀 값의 합이다. 그리고, α는 가중치, β는 바이어스, γ는 객체 환경 변수이다. From here,

Is the object pixel value,

Is the sum of total pixel values incident on the infrared camera 110, that is, object pixel values and object environment pixel values. And, α is a weight, β is a bias, and γ is an object environment variable.

The infrared image receiving unit 330 receives the infrared image of the target object from the infrared camera 110. The object classifying unit 350 extracts an object pixel value based on the learning contents learned through the infrared image learning unit 310 from the infrared image of the target object, a range of object pixel values for each preset object, and the extracted object pixel Target objects are classified based on comparison between values.

Here, the object classification unit 350 may extract the object pixel value of the target object as shown in [Equation 3] below.

는 타깃 객체의 객체 픽셀 값,

는 적외선 영상 수신부(330)를 통해 수신된 타깃 객체의 총 픽셀 값, 즉 타깃 객체의 객체 픽셀 값 및 객체 환경 픽셀 값의 합이다. 그리고, α'는 적외선 영상 학습부(310)에 의해 학습된 가중치 값, β'는 적외선 영상 학습부(310)에 의해 학습된 바이어스 값이며, γ는 객체 환경 변수이다. From here,

Is the object pixel value of the target object,

Is the sum of the total pixel values of the target object received through the infrared image receiver 330, that is, the object pixel values of the target object and the object environment pixel values. In addition, α 'is a weight value learned by the infrared image learning unit 310, β' is a bias value learned by the infrared image learning unit 310, and γ is an object environment variable.

That is, the object classification unit 350 extracts only the object pixel values of the target object excluding pixel values due to the surrounding environment and geographic conditions of the target object using the weight value and the bias value learned through the infrared image learning unit 310. can do. The object classifying unit 350 may classify a target object by matching a range of a preset object pixel value for each object and an extracted object pixel value. Here, the range of object pixel values may include a minimum value and a maximum value set based on the object pixel values of the corresponding object itself.

The control unit 370 may control the overall operation of the image analysis device 120 and manage a control flow or data flow between the infrared image learning unit 310, the infrared image receiving unit 330, and the object classification unit 350. .

FIG. 4 is a flowchart illustrating an infrared image analysis method performed in the image analysis device of FIG. 1.

In FIG. 4, the infrared image learning unit 310 acquires an infrared image obtained by photographing an object in the object learning population with an infrared camera (step S410). Next, the infrared image learning unit 310 inputs the object pixel values of the object itself, the object environment pixel values, and the object environment variables corresponding to the surrounding environment of the object, as the input values of the AI algorithm, detected from the acquired infrared image. (Step S420).

Then, the infrared image learning unit 310 calculates the weight and bias corresponding to the surrounding environment of the object according to Equation 2 described above (step S430). That is, the infrared image learning unit 310 inputs the object pixel value of the object itself, the object pixel value of the object affected by the surrounding environment, the object environment pixel value, and the object environment variable into the artificial intelligence algorithm, and the influence of the surrounding environment In order to extract the object pixel value of the excluded object itself, a process of outputting weights and biases is performed. The infrared image learning unit 310 may perform learning in consideration of the surrounding environment of various conditions for each object existing in the AI object learning population.

Then, the infrared image receiving unit 330 receives an infrared image of the target object (step S440), and the object classification unit 350 receives the learning result of the infrared image learning unit 310 from the infrared image of the received target object. Based on this, the object pixel value of the target object is extracted (step S450).

)을 입력하고, 동시에 적외선 영상 학습부(310)에 의해 산출된 가중치(α')값, 바이어스(β')값, 현재 타깃 객체의 주변 환경에 대응하는 객체 환경 변수(γ)를 입력한다. 이를 통해, 객체 분류부(350)는 타깃 객체 자체의 객체 픽셀 값(

)을 추출할 수 있다.The object classification unit 350 adds the object pixel value and the object environment pixel value from the infrared image of the received target object, as shown in [Equation 3] above.

), And at the same time, input the weight (α ') value, the bias (β') value, and the object environment variable (γ) corresponding to the surrounding environment of the current target object, calculated by the infrared image learning unit 310. Through this, the object classification unit 350 may generate an object pixel value of the target object itself (

) Can be extracted.

Then, the object classification unit 350 classifies the target object by matching the object pixel value of the extracted target object to a range of object pixel values for each preset object (step S460). That is, the image analysis method according to an embodiment of the present invention corrects an object pixel value fluctuated by the surrounding environment of the target object with an object pixel value of only the target object, and then classifies the target object with the corrected object pixel value. Target objects can be accurately determined.

The image analysis device 130 may be combined with a driving control system (not shown) of an autonomous vehicle to control driving or braking of the autonomous vehicle. Hereinafter, it will be described in detail with reference to FIGS. 5 and 6.

5 and 6 are diagrams illustrating a process of performing infrared image analysis by applying the image analysis device of FIG. 1 to an autonomous vehicle.

In FIG. 5, the image analysis device 130 may receive an infrared image of the target object 520, for example, a pedestrian, through the infrared camera 110 disposed in the autonomous vehicle 510. Here, the case where the infrared camera 110 is disposed outside the autonomous vehicle 510 is illustrated, for example, but the position of the infrared camera 110 may be changed.

)은 40.2°에 대응하는 값일 수 있다. 영상 분석 장치(130)는 30°의 기온과 정오의 태양 위치 등에 대응하는 객체 환경 변수(γ), 타깃 객체(520)의 주위 환경 및 지리적 조건에 대응하여 미리 학습된 가중치(α')값 및 바이어스(β')값을 이용하여 타깃 객체(520)만의 객체 픽셀 값(

)(530)을 산출한다.Here, the current temperature is 30 °, and at noon, the total pixel value of the target object 520 detected from the received infrared image (

) May be a value corresponding to 40.2 °. The image analysis device 130 includes an object environment variable (γ) corresponding to a temperature of 30 ° and a solar location at noon, a weight (α ′) value previously learned in response to the surrounding environment and geographic conditions of the target object 520, and The object pixel value of the target object 520 using the bias (β ') value (

) (530).

That is, as illustrated in FIG. 6, the temperature A of the target object 520 may be changed by being influenced by the surrounding environment and geographic conditions. Accordingly, the image analysis apparatus 130 according to an embodiment of the present invention corrects the temperature A of the changed target object 520 to the temperature B of only the target object 520 to influence the influence of the surrounding environment and geographical conditions. It can be minimized.

For example, the image analysis device 130 may correct the temperature of the target object 520 from 40.2 ° to 36.5 °. Then, the image analysis device 130 may classify the target object 520 as a pedestrian when the temperature of the corrected target object 520 corresponds to a preset range of pixel values of the pedestrian, for example, 36 ° to 37 °. You can.

As described above, when the target object 520 is classified as a pedestrian through the image analysis device 130, the autonomous driving vehicle calculates the distance between the pedestrian and the vehicle through the driving control system, and when the pedestrian enters the vehicle within a predetermined distance The vehicle can be stopped.

Although described above with reference to preferred embodiments of the present invention, those skilled in the art variously modify and change the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You can understand that you can.

100: video analysis system
110: infrared camera 130: image analysis device
150: database 310: infrared image learning unit
330: infrared image receiving unit 350: object classification unit
370: control

Claims (8)

An infrared image learning unit for performing machine learning by receiving an object pixel value and an object environment pixel value detected from an infrared image of an object in the object learning population and an object environment variable affected by the surrounding environment;
An infrared image receiver configured to receive a corresponding infrared image related to a target object; And
And an object classifying unit to classify the target object by extracting a pixel value of the corresponding object based on the learning content of the machine learning from the corresponding infrared image.
The infrared image learning unit
Machine learning is performed by using the object pixel value, the object environment pixel value, and the object environment variable as inputs, and outputting weights and biases according to the surrounding environment,
The infrared image learning unit image analysis device characterized in that for performing the machine learning according to the [Mathematics] below.
[Mathematics]

(Here,

Is the object pixel value, the

Is the sum of the object pixel value and the object environment pixel value, the α is the weight, the β is the bias, and γ is the object environment variable) delete delete The method of claim 1, wherein the object classification unit
The corresponding object pixel value is extracted from the infrared image of the target object by using the machine-learned weight and bias corresponding to the surrounding environment of the target object, a range of object pixel values for each preset object and the corresponding object extracted And classifying the target object based on a comparison between pixel values.
The image analysis apparatus according to claim 4, wherein the object classification unit extracts the object pixel value of the target object according to the following equation.
[Mathematics]

(Here,

Is the object pixel value of the target object, the

Is the sum of the object pixel values of the target object and the object environment pixel values, the α 'is the machine-learned weight, the β' is the machine-learned bias, and the γ is the object environment variable)
The image analysis apparatus of claim 1, wherein the object pixel value and the object environment pixel value are values corresponding to any one of an infrared signal, an apparent temperature, and an RGB value.
Inputting object pixel values and object environment pixel values detected from an infrared image of an object in an object learning population and object environment variables affected by the surrounding environment, and performing machine learning to calculate weights and biases according to the surrounding environment;
Receiving a corresponding infrared image related to the target object; And
And extracting a corresponding object pixel value from the corresponding infrared image using the calculated weight and bias, and classifying the target object using the extracted corresponding object pixel value.
The machine learning is performed by inputting the object pixel value, the object environment pixel value, and the object environment variable, and outputting weights and biases according to the surrounding environment as outputs,
The machine learning is an image analysis method, characterized in that is performed according to the following [Mathematics].
[Mathematics]

(Here,

Is the object pixel value, the

Is the sum of the object pixel value and the object environment pixel value, the α is the weight, the β is the bias, and γ is the object environment variable)
The method of claim 7, wherein the step of classifying the target object is
And matching the extracted object pixel values to a range of object pixel values for each preset object.

Images