JP-2026075252-A - Subject detection device, subject detection method, program and storage medium thereof
Abstract
[Problem] The present invention aims to accurately detect objects in a camera system equipped with haze correction. [Solution] A subject detection device comprising: an imaging means for capturing a visible light image; a detection means for detecting a target for detection; a modification means for changing the threshold of the target for detection; a processing means for performing correction processing related to contrast; a selection means for selecting one setting from a plurality of settings including a first setting and a second setting corrected by the processing means so that the contrast is lower than the first setting; and a modification means for changing the threshold of the subject based on the contrast setting. [Selection Diagram] Figure 7
Inventors
- 大森 広崇
Assignees
- キヤノン株式会社
Dates
- Publication Date
- 20260508
- Application Date
- 20241022
Claims (11)
- An imaging means for capturing a visible light image, A detection means for detecting subjects exceeding a threshold in the images captured by the aforementioned imaging means, A means for changing the threshold, The imaging means performs contrast correction on the image it captures, A selection means for selecting one setting from a plurality of settings, including a first setting and a second setting which the processing means corrects so that the contrast is lower than that of the first setting. A changing means for changing the threshold value of a predetermined subject in the visible light image when the first setting is set to be higher than the threshold value of the predetermined subject in the visible light image when the second setting is set, A subject detection device characterized by having the following features.
- The subject detection device according to claim 1, characterized in that the correction is haze correction.
- A means for acquiring information about a subject using radar, The subject detection device according to claim 1, characterized in that the modifying means makes the threshold of the predetermined subject different in a first region and a second region different from the first region in the visible light image, based on the acquisition means.
- A means for acquiring information about a subject using radar, The subject detection device according to claim 1, further comprising a setting means for setting a detection range, which is the range in which the detection means performs detection of the object to be detected, based on the information acquired by the acquisition means.
- A means for acquiring information about a subject using radar, The subject detection device according to claim 1, further comprising a size setting means for setting the detection size of the object to be detected based on the information acquired by the acquisition means.
- The subject detection device according to claim 1, characterized in that the selection means automatically selects one setting from the plurality of settings based on the visible light image.
- The subject detection device according to claim 6, characterized in that the selection means automatically selects one setting from the plurality of settings based on a histogram relating to the brightness of the visible light image.
- The system includes a means for determining the weather from the visible light image, The subject detection device according to claim 1, characterized in that, based on the weather determined by the determination means, the selection means selects one setting from the plurality of settings.
- A method for controlling a subject detection device, The imaging process involves capturing a visible light image, The aforementioned imaging step includes a detection step that detects subjects exceeding a threshold from the image captured by the imaging step as subjects to be detected, A modification step to change the threshold, The imaging means performs a processing step to correct the contrast of the image it captures, A selection step of selecting one setting from a plurality of settings, including a first setting and a second setting which the processing step corrects so that the contrast is lower than that of the first setting. A modification step of changing the threshold value of a predetermined subject in the visible light image when the first setting is set to be higher than the threshold value of the predetermined subject in the visible light image when the second setting is set, A subject detection method characterized by having the following features.
- A program for causing at least one computer to function as each of the means of the subject detection device described in claim 1.
- A computer-readable storage medium containing a program for causing at least one computer to function as each means of the subject detection device described in claim 1.
Description
This invention relates to a subject detection device and method for detecting subjects, and to an imaging system thereof. Conventional subject detection devices are expected to be usable in a variety of environments. When subject detection devices are used, the environment is not always ideal for photography, and photography techniques adapted to the specific environment are required. When subject detection devices are used on ships, for example, the subject may be obscured by fog or haze. In such environments, attempting to detect a subject using visible light images results in low contrast and poor visibility, leading to a decrease in the accuracy of subject detection. Therefore, technologies have been disclosed that use information other than visible light images to detect subjects. Patent Document 1 discloses a technology that uses visible light images and information obtained from radar or infrared sources other than visible light images to detect subjects. Japanese Patent Publication No. 2007-255979 A block diagram showing the configuration of an image processing system according to Embodiment 1 of the present invention.A flowchart illustrating the image processing according to Embodiment 1.A diagram showing a visible light camera according to Embodiment 1 and information acquired by radar.A diagram illustrating the grayscale correction process according to Embodiment 1.A diagram illustrating a method for setting the detection range based on subject information according to Embodiment 1.A diagram illustrating the method for setting the detection size based on subject information according to Embodiment 1.A diagram illustrating a method for setting the subject threshold based on haze correction intensity according to Embodiment 1.A diagram illustrating subject information according to Embodiment 2 and a method for setting the subject threshold based on haze correction intensity. This embodiment will be described in detail below with reference to the drawings. Furthermore, one or more of the functional blocks shown in the diagram below may be implemented by hardware such as ASICs or programmable logic arrays (PLAs), or by a programmable processor such as a CPU or MPU executing software. They may also be implemented by a combination of software and hardware. Therefore, even if different functional blocks are described as the primary operating components in the following explanation, the same hardware may be the primary implementing component. ASIC stands for Application Specific Integrated Circuit. CPU stands for Central Processing Unit. MPU stands for Micro-Processing Unit. <First Embodiment> Figure 1 is a diagram illustrating the configuration of an imaging system according to Embodiment 1 of the present invention. The visible light camera 11 captures visible light. The visible light camera 11 includes an imaging optical system containing one or more lenses, and a visible light image sensor (visible light sensor) that captures the optical image formed by the imaging optical system and converts it into an electrical signal. The visible light sensor detects visible light in the wavelength range of approximately 380 nm to approximately 750 nm, for example. The visible light sensor may have sensitivity in at least a portion of the near-infrared wavelength range. Radar 12 measures the size, distance, and direction of an object. By emitting short-wavelength microwaves and measuring the time elapsed since the reflected waves from the object, it can obtain, for example, the object's size, distance, and direction. Furthermore, based on AIS (Automatic Identification System) and GPS (Global Positioning System) information, it is possible to superimpose and link ship information and nautical chart data to the measured object. The visible light image acquisition unit 101 acquires the visible light image captured by the visible light camera 11. The radar information acquisition unit 102 acquires subject information measured by the radar 12. In this embodiment, the subject information includes, as described above, information such as the size, distance, and direction of the subject. However, it is not limited to this; it may also include temperature information, weather, position and direction information, and speed information of subjects such as ships, people, and animals. The gradation correction processing unit 103 performs correction processing on images with reduced contrast based on the images acquired from the visible light camera 11. The subject detection unit 104 detects a subject in an image that has undergone grayscale correction processing, based on subject information obtained from the radar information acquisition unit 102 and at least one piece of image processing parameter information obtained from the grayscale correction processing unit 103. Various methods can be employed for subject detection, such as pattern matching, methods using luminance gradients within local regions, and machine learning-b