CN110795348A - Image ranging automatic testing device and method based on data playback - Google Patents
Image ranging automatic testing device and method based on data playback Download PDFInfo
- Publication number
- CN110795348A CN110795348A CN201911029557.7A CN201911029557A CN110795348A CN 110795348 A CN110795348 A CN 110795348A CN 201911029557 A CN201911029557 A CN 201911029557A CN 110795348 A CN110795348 A CN 110795348A
- Authority
- CN
- China
- Prior art keywords
- test
- module
- test case
- target version
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 249
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012795 verification Methods 0.000 claims abstract description 10
- 238000004140 cleaning Methods 0.000 claims abstract description 8
- 238000013461 design Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000011161 development Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/368—Test management for test version control, e.g. updating test cases to a new software version
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic testing device and method for image ranging based on data playback, belonging to the field of driving assistance systems, and the device comprises: the system comprises a historical data processing module, a test case design module, an automatic test module and a verification module; the historical data processing module is used for collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library including various types of test scenes; the test case design module is used for designing a plurality of test cases and marking an expected result for each test case, and each scene in the scene library corresponds to one test case; the automatic test module is used for testing the target version algorithm by adopting each test case to obtain test results under various types of test scenes; and the verification module is used for comparing each test result with the corresponding expected result so as to verify the accuracy of the target version algorithm. The invention can improve the testing efficiency and reduce the testing time.
Description
Technical Field
The invention belongs to the field of driving assistance systems, and particularly relates to an automatic image ranging testing device and method based on data playback.
Background
The image distance measuring function of the Advanced Driving Assistance System (ADAS) device of the automobile can measure the distance between the automobile and the front vehicle and the pedestrian by using the image collected by the camera, thereby giving an early warning to the driver under the possible dangerous condition.
For the test of the image ranging function, the existing test scheme at present is as follows: after the ranging algorithm is developed, the ranging algorithm is integrated into ADAS equipment firmware, after a tester verifies basic functions of the firmware, the tester drives the vehicle to a field to test ranging functions, and after data is collected, the test result is processed and generated.
The existing test scheme aiming at the image ranging function is low in time consumption, labor consumption and efficiency, and the defects of the existing test scheme are mainly shown in the following aspects:
(1) in each test, the vehicle is driven to a field site for testing, and a large amount of labor, time and cost are consumed.
(2) Test conditions are difficult to construct: the image ranging function is affected by a variety of environmental conditions: light (light and shade intensity, angle, contrast, color temperature, etc.), road conditions (road surface conditions, isolation belts, green belt conditions, etc.), front obstacle types (vehicle occupants, size, shape, color, etc.), front obstacle motion state (transverse and longitudinal speed), weather (frost, rain, snow, etc.), etc. Each test covers various scenarios. Some of the scene conditions are difficult to construct and can be realized only by consuming time and labor or waiting for time.
(3) Historical test video material cannot be reused.
(4) Each time of testing various scenes, due to the limitation of manpower, vehicles and places, the testing can only be carried out in series, so that a complete testing period is very long.
(5) The algorithmic verification relies on the device system firmware. Each verification process needs to be finished after the development of the device system firmware, and if the firmware has basic functional problems, the test activities cannot be carried out.
Disclosure of Invention
Aiming at the defects or the improvement requirements of the prior art, the invention provides an automatic image ranging testing device and method based on data playback, so that the technical problems of low efficiency, long time consumption and the like in the image ranging function test of the conventional automobile advanced driving assistance system equipment are solved.
To achieve the above object, according to one aspect of the present invention, there is provided an automatic test apparatus for image ranging based on data playback, comprising: the system comprises a historical data processing module, a test case design module, an automatic test module and a verification module;
the historical data processing module is used for collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library including various types of test scenes;
the test case design module is used for designing a plurality of test cases and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
the automatic test module is used for testing the target version algorithm by adopting each test case to obtain a test result of each test case under a corresponding type test scene;
the verification module is used for comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
Preferably, the apparatus further comprises: a test case updating module;
and the test case updating module is used for automatically compiling the new target version algorithm to generate a new version test case program after the target version algorithm is updated.
Preferably, the automated testing module comprises:
the distribution module is used for distributing each test case to a corresponding execution machine to be executed so as to enable each execution machine to execute the test operation of the target version algorithm;
and the test result summarizing module is used for respectively collecting the test results obtained by the execution machines, wherein each type of test scene corresponds to one test result.
Preferably, the apparatus further comprises: a test result notification module;
and the test result notification module is used for sending the test results of the target version algorithm under various types of test scenes to target personnel.
Preferably, each of the execution machines executes test operations in parallel.
According to another aspect of the present invention, there is provided an automated testing method for image ranging based on data playback, comprising:
(1) collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library comprising various types of test scenes;
(2) designing a plurality of test cases, and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
(3) testing the target version algorithm by adopting each test case to obtain a test result of each test case under a test scene of a corresponding type;
(4) and comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
Preferably, before step (3), the method further comprises:
and after the target version algorithm is updated, automatically compiling the new target version algorithm to generate a new version test case program.
Preferably, step (3) comprises:
distributing each test case to a corresponding execution machine for execution so as to enable each execution machine to execute the test operation of the target version algorithm;
and respectively collecting the test results obtained by each execution machine, wherein each type of test scene corresponds to one test result.
Preferably, the method further comprises:
and sending the test result of the target version algorithm under various types of test scenes to target personnel.
Preferably, each of the execution machines executes test operations in parallel.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
1. according to the invention, the scene libraries are established through the historical data, and the test case programs corresponding to the scene libraries are designed, so that the test mode can be executed all day long, and the test result can be obtained at any time. As long as a new version is developed, the automated test can be started to obtain a test result.
2. The invention adopts a plurality of executors to execute the test operation in parallel, and the test period of the test mode is short. The original test period is in units of weeks, and the current test period only needs a few hours.
3. Historical test video materials in the scene library can be reused without repeated construction.
4. The invention adopts historical scene data for testing, does not need to construct or wait for testing environmental conditions (such as weather, light, road conditions and the like), and does not need vehicles, fields and out-of-office testers, so that the developed algorithm can be independently verified in advance without being limited by the development progress of equipment system firmware.
Drawings
FIG. 1 is a schematic structural diagram of an automated testing apparatus for image ranging based on data playback according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of an automated testing method for image ranging based on data playback according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention relates to an automatic testing device and method for a distance measuring function of an ADAS (advanced driver assistance System) device of an automobile.
Fig. 1 is a schematic structural diagram of an automatic testing apparatus for image ranging based on data playback according to an embodiment of the present invention, where the apparatus shown in fig. 1 includes: the system comprises a historical data processing module, a test case design module, an automatic test module and a verification module;
the historical data processing module is used for collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library including various types of test scenes;
in the embodiment of the present invention, the historical test data may include video, radar data, and the like, and the collected historical test data needs to cover various test scenarios, for example: testing data under light scenes with different light and shade intensities, angles, contrast ratios, color temperatures and the like; testing data under various road conditions, isolation zones, green belt conditions and other road conditions; test data under a variety of different front obstacle type (e.g., car, person, obstacle size, shape color, etc.) scenarios; test data under different scenes of the motion state (such as transverse and longitudinal speeds) of the front obstacle; test data and the like under various weather (such as frost, rain, snow and the like) scenes; and performing finishing and cleaning.
The test case design module is used for designing a plurality of test cases and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
in the embodiment of the invention, each test case can correspond to a section of historical video in a scene.
Wherein the expected result in the embodiment of the invention represents an expected correct output result.
The automatic test module is used for testing the target version algorithm by adopting each test case to obtain a test result of each test case under a test scene of a corresponding type;
in the embodiment of the present invention, after the test is started, the target in front of the vehicle in each test scenario can be identified, for example: lane identification, preceding vehicle identification, pedestrian identification, sign identification, and the like. After the target is identified, an alarm process may be performed according to the ranging function of the target version algorithm to obtain a test result, for example: lane departure, preceding vehicle collision early warning, pedestrian early warning, collision time early warning and the like.
In an embodiment of the present invention, an automated testing module includes:
the distribution module is used for distributing each test case to the corresponding execution machine to be executed so as to enable each execution machine to execute the test operation of the target version algorithm;
and the test result summarizing module is used for respectively collecting the test results obtained by the execution machines, wherein each type of test scene corresponds to one test result.
In an embodiment of the present invention, the apparatus further includes: a test case updating module;
and the test case updating module is used for automatically compiling the new target version algorithm to generate a new version test case program after the target version algorithm is updated.
And the verification module is used for comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
In an embodiment of the present invention, the apparatus further includes: a test result notification module;
and the test result notification module is used for sending the test results of the target version algorithm under various types of test scenes to the target personnel.
Wherein, the information can be sent to relevant personnel for testing, development and the like through mails and the like.
Wherein, each executive machine executes the test operation in parallel, and the test period is greatly shortened.
Fig. 2 is a schematic flowchart of an automated testing method for image ranging based on data playback according to an embodiment of the present invention, where the method shown in fig. 1 includes:
s1: collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library comprising various types of test scenes;
s2: designing a plurality of test cases, and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
s3: testing the target version algorithm by adopting each test case to obtain a test result of each test case under a test scene of a corresponding type;
in an embodiment of the present invention, step (3) includes:
distributing each test case to a corresponding execution machine for execution so as to enable each execution machine to execute the test operation of the target version algorithm;
and respectively collecting test results obtained by each execution machine, wherein each type of test scene corresponds to one test result.
Wherein the execution machines execute test operations in parallel.
In an embodiment of the present invention, before step (3), the method further includes:
and after the target version algorithm is updated, automatically compiling the new target version algorithm to generate a new version test case program.
S4: and comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
In an embodiment of the present invention, the method further includes:
and sending the test result of the target version algorithm under each type of test scene to the target personnel.
It should be noted that, according to the implementation requirement, each step/component described in the present application can be divided into more steps/components, and two or more steps/components or partial operations of the steps/components can be combined into new steps/components to achieve the purpose of the present invention.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An automated testing device for image ranging based on data playback, comprising: the system comprises a historical data processing module, a test case design module, an automatic test module and a verification module;
the historical data processing module is used for collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library including various types of test scenes;
the test case design module is used for designing a plurality of test cases and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
the automatic test module is used for testing the target version algorithm by adopting each test case to obtain a test result of each test case under a corresponding type test scene;
the verification module is used for comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
2. The apparatus of claim 1, further comprising: a test case updating module;
and the test case updating module is used for automatically compiling the new target version algorithm to generate a new version test case program after the target version algorithm is updated.
3. The apparatus of claim 1 or 2, wherein the automated test module comprises:
the distribution module is used for distributing each test case to a corresponding execution machine to be executed so as to enable each execution machine to execute the test operation of the target version algorithm;
and the test result summarizing module is used for respectively collecting the test results obtained by the execution machines, wherein each type of test scene corresponds to one test result.
4. The apparatus of claim 1, further comprising: a test result notification module;
and the test result notification module is used for sending the test results of the target version algorithm under various types of test scenes to target personnel.
5. The apparatus of claim 3,
and each executing machine executes the test operation in parallel.
6. An automatic testing method of image ranging based on data playback is characterized by comprising the following steps:
(1) collecting historical test data covering various types of test scenes, and sorting and cleaning the historical test data to obtain a scene library comprising various types of test scenes;
(2) designing a plurality of test cases, and marking an expected result for each test case, wherein each scene in the scene library corresponds to one test case;
(3) testing the target version algorithm by adopting each test case to obtain a test result of each test case under a test scene of a corresponding type;
(4) and comparing the test result corresponding to each test case with the expected result corresponding to each test case so as to verify the accuracy of the target version algorithm.
7. The method of claim 6, wherein prior to step (3), the method further comprises:
and after the target version algorithm is updated, automatically compiling the new target version algorithm to generate a new version test case program.
8. The method of claim 6 or 7, wherein step (3) comprises:
distributing each test case to a corresponding execution machine for execution so as to enable each execution machine to execute the test operation of the target version algorithm;
and respectively collecting the test results obtained by each execution machine, wherein each type of test scene corresponds to one test result.
9. The method of claim 6, further comprising:
and sending the test result of the target version algorithm under various types of test scenes to target personnel.
10. The method of claim 8,
and each executing machine executes the test operation in parallel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029557.7A CN110795348A (en) | 2019-10-28 | 2019-10-28 | Image ranging automatic testing device and method based on data playback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029557.7A CN110795348A (en) | 2019-10-28 | 2019-10-28 | Image ranging automatic testing device and method based on data playback |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110795348A true CN110795348A (en) | 2020-02-14 |
Family
ID=69441503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911029557.7A Pending CN110795348A (en) | 2019-10-28 | 2019-10-28 | Image ranging automatic testing device and method based on data playback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110795348A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908540A (en) * | 2017-07-26 | 2018-04-13 | 平安壹钱包电子商务有限公司 | Test case creation method, apparatus, computer equipment and medium |
| CN109446371A (en) * | 2018-11-09 | 2019-03-08 | 苏州清研精准汽车科技有限公司 | A kind of intelligent automobile emulation testing scene library generating method and test macro and method |
| CN109614704A (en) * | 2018-12-11 | 2019-04-12 | 安徽江淮汽车集团股份有限公司 | A kind of ADAS automatization test system and method |
-
2019
- 2019-10-28 CN CN201911029557.7A patent/CN110795348A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908540A (en) * | 2017-07-26 | 2018-04-13 | 平安壹钱包电子商务有限公司 | Test case creation method, apparatus, computer equipment and medium |
| CN109446371A (en) * | 2018-11-09 | 2019-03-08 | 苏州清研精准汽车科技有限公司 | A kind of intelligent automobile emulation testing scene library generating method and test macro and method |
| CN109614704A (en) * | 2018-12-11 | 2019-04-12 | 安徽江淮汽车集团股份有限公司 | A kind of ADAS automatization test system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108318043B (en) | Method, apparatus, and computer-readable storage medium for updating electronic map | |
| CN102073846B (en) | Method for acquiring traffic information based on aerial images | |
| US20200364467A1 (en) | Method and device for detecting illegal parking, and electronic device | |
| DE102016123887A1 (en) | VIRTUAL SENSOR DATA GENERATION FOR WHEEL STOP DETECTION | |
| CN105702152A (en) | Map generation method and device | |
| CN107003671B (en) | Positioning and mapping method and system | |
| CN109272034B (en) | Missing vehicle license plate prediction method and processing terminal | |
| CN111079680B (en) | Temporary traffic signal lamp detection method and device and automatic driving equipment | |
| CN106023622B (en) | A kind of method and apparatus of determining traffic lights identifying system recognition performance | |
| CN103124978B (en) | Guiding device and guidance method | |
| CN110853366A (en) | Method and device for detecting parking position of vehicle | |
| CN112525552A (en) | Algorithm test system and method for automobile advanced auxiliary driving system | |
| CN114091626A (en) | True value detection method, device, equipment and storage medium | |
| CN110795348A (en) | Image ranging automatic testing device and method based on data playback | |
| CN103077614B (en) | Method for detecting pedestrian crossing vehicles based on computer vision | |
| CN116580271A (en) | Evaluation method, device, equipment and storage medium for perception fusion algorithm | |
| CN111311601A (en) | Segmentation method and device for spliced image | |
| US20220223047A1 (en) | Computer-implemented method for determining similarity values of traffic scenarios | |
| Saha et al. | Road Rutting Detection using Deep Learning on Images | |
| CN116783626A (en) | Method for training a camera-based control system and training system | |
| CN111661054B (en) | Vehicle control method, device, electronic device and storage medium | |
| Xiang et al. | Automatic vehicle identification in coating production line based on computer vision | |
| Afdhal et al. | Evaluation of benchmarking pre-trained cnn model for autonomous vehicles object detection in mixed traffic | |
| CN113848826A (en) | Automatic vehicle offline method, device, equipment and storage medium | |
| CN110718066A (en) | License plate recognition method, medium, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |