JP-7856503-B2 - Object detection device and object detection method

JP7856503B2JP 7856503 B2JP7856503 B2JP 7856503B2JP-7856503-B2

Inventors

今城健治
上林輝彦

Assignees

株式会社デンソーテン

Dates

Publication Date: 20260511
Application Date: 20220617

Claims (6)

An object detection device mounted on a moving object, The system includes a control unit that detects the target object when the confidence level included in the image recognition result for a camera image of a learning model that has learned the features of the target object exceeds a threshold. The control unit, When detecting a series of objects consisting of one or more consecutive objects of the same type in the camera image as the object to be detected, a second threshold lower than a predetermined first threshold is set to the threshold. If the recovery condition is met, which determines that the continuity of detection of the continuous object has been interrupted, the first threshold is set to the threshold; if the recovery condition is met and the first continuous object is detected, the second threshold is set to the threshold. Object detection device.
The control unit, The second threshold is set to the threshold from the time the continuous detection object is detected until the return condition is met. The object detection device according to claim 1 .
The control unit, The return condition is defined as the moving body moving a predetermined distance after the continuous detection of the object ceases to be detected. The object detection device according to claim 2 .
The control unit, If the moving speed of the moving body is 0, the first threshold is set to the threshold. The object detection device according to claim 1.
The aforementioned continuous detection object is a traffic light or a road sign. An object detection device according to any one of claims 1 to 4 .
An object detection method performed by an object detection device mounted on a moving object, The detection of the target object occurs when the confidence level included in the image recognition result for a camera image of a learning model that has learned the features of the target object exceeds a threshold. When detecting a series of objects consisting of one or more consecutive objects of the same type in the camera image as the object to be detected, a second threshold lower than a predetermined first threshold is set to the threshold. If the recovery condition is met, which determines that the continuity of detection of the continuous detection object has been interrupted, the first threshold is set to the threshold; if the recovery condition is met and the first continuous detection object is detected, the second threshold is set to the threshold; An object detection method, including the following.

Description

The embodiments of the disclosure relate to an object detection device and an object detection method. Conventionally, technologies for detecting traffic lights from camera images captured by an on-board camera in front of a vehicle are known. Such technologies include, for example, those that detect traffic lights by setting the location of traffic lights pre-registered in map information as the detection target area (see, for example, Patent Document 1). Furthermore, some such technologies use machine learning algorithms, such as deep learning, to extract areas in camera images that are estimated to contain traffic lights as detection frames, and then detect traffic lights based on the confidence level of these detection frames. Japanese Patent Publication No. 2020-027328 Figure 1 shows an example of the mounting of an object detection device according to the embodiment.Figure 2 is a schematic diagram (part 1) illustrating the object detection method according to the embodiment.Figure 3 is a schematic diagram (part 2) illustrating the object detection method according to the embodiment.Figure 4 is a block diagram showing an example configuration of an object detection device according to an embodiment.Figure 5 is an explanatory diagram of the first modified example.Figure 6 is an explanatory diagram of the second modified example.Figure 7 is a flowchart showing the processing procedure performed by the object detection device according to the embodiment. The embodiments of the object detection device and object detection method disclosed herein will be described in detail below with reference to the attached drawings. However, this invention is not limited to the embodiments described below. Furthermore, in the following, we will assume that the objects to be detected are those that appear consecutively in the camera image, such as traffic lights, where one or more of the same type are present. Such objects will be referred to as "consecutive detection objects" as appropriate. In this embodiment, we will give an example where such consecutive detection objects are traffic lights. Since traffic lights rarely exist individually at a single intersection, they can be considered consecutive detection objects. First, an overview of the object detection device and object detection method according to the embodiment will be described using Figures 1 to 3. Figure 1 is a diagram showing an example of the object detection device 10 according to the embodiment. Figures 2 and 3 are schematic diagrams (part 1) and (part 2) illustrating the object detection method according to the embodiment. As shown in Figure 1, the object detection device 10 according to this embodiment is, for example, mounted on a vehicle V, and detects objects by image recognition processing based on camera images captured by the camera 11 (see Figure 4) of the object detection device 10. In the example shown in Figure 1, the object detection device 10 is a drive recorder mounted to capture images of the area in front of the vehicle V. Note that the object detection device 10 may be a separate device from the drive recorder, and may be configured to detect objects from camera images surrounding the vehicle V, including the rear and sides, in addition to the area in front of the vehicle V. For example, the object detection device 10 uses a deep learning algorithm to perform image recognition processing to detect a traffic light, which is the object to be detected, from a camera image taken in front of the vehicle V. More specifically, the object detection device 10 uses a learning model that has learned the features of the object to be detected using a deep learning algorithm, and detects objects within the detection frame where the confidence level included in the image recognition result of the learning model for the camera image exceeds a preset threshold. In this type of machine learning-based object detection method, the larger the object to be detected in the camera image, the more accurately it can be detected. Conversely, the smaller the object to be detected in the camera image, the lower the detection accuracy tends to be. In other words, the further the object is from the vehicle V, the smaller it appears in the camera image, leading to a decrease in detection accuracy. More specifically, as shown in Figure 2, for example, the detection frames BB1 to BB5 of a traffic light tend to increase in size the closer they are to vehicle V, and decrease in size the further they are from vehicle V. Furthermore, smaller detection frames result in fewer features, which in turn leads to lower confidence levels. In such cases, if the confidence threshold is a uniform value, traffic lights tend to be detected more easily the closer they are to vehicle V, but conversely, they may not be detected at all the further away they are. In the example in Figure 2, for example, if the uniform confidence threshold is "0.5", detection frames BB1 and BB2 will be det