CN112581470A - Small target object detection method - Google Patents
Small target object detection method Download PDFInfo
- Publication number
- CN112581470A CN112581470A CN202011639587.2A CN202011639587A CN112581470A CN 112581470 A CN112581470 A CN 112581470A CN 202011639587 A CN202011639587 A CN 202011639587A CN 112581470 A CN112581470 A CN 112581470A
- Authority
- CN
- China
- Prior art keywords
- characteristic image
- characteristic
- image
- target object
- small target
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 238000005070 sampling Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 12
- 238000003062 neural network model Methods 0.000 description 7
- 230000001580 bacterial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Abstract
The invention discloses a small target object detection method, which relates to the technical field of computers, and is characterized in that each time of convolution and downsampling is carried out to collect a characteristic image, each time of characteristic image is superposed with a characteristic output by downsampling next time, so that the small target object is predicted by using a large-size characteristic image with less lost information, a large target object is predicted by using a small-size characteristic image with more abstract semantic information obtained through multiple times of convolution, and the accuracy of a prediction result is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a small target object detection method.
Background
For the detection of small target objects such as colonies, the traditional scheme is to culture the colonies on a culture dish, observe the colonies with human eyes, mark the colonies on the culture dish with a black marker pen, and count the colonies. The whole process is large in workload, tedious and tedious, and much in repetitive labor, and because many bacterial colonies are very fine, human eyes can easily see the bacterial colonies in the counting process, the bacterial colonies need to be gathered to see mentally, fatigue is easily caused, the efficiency is low, and the labor cost is high.
In order to improve efficiency and reduce labor cost, the conventional detection of small target objects mainly performs convolution and pooling operations on original images through a convolution neural network model to obtain feature images with different sizes, predicts the feature image of the last layer, ignores the feature images of other layers and is low in accuracy.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a small target object detection method, which comprises the following steps:
s1, continuously and repeatedly carrying out down-sampling on the original image where the small target object is located by using the convolutional neural network model to obtain a plurality of characteristic images;
s2, the convolutional neural network model sorts the plurality of feature images according to the time sequence of the down sampling to obtain a feature image group;
s3 selecting the last n characteristic images in the characteristic image group by the convolutional neural network model, and sequentially marking the n characteristic images as C according to the size sequence1、C2、C3…Cn；
S4 characteristic image C is processed by using convolution neural network modelnPerforming convolution operation by 1 to obtain a characteristic image Mn；
S5 performing M on the characteristic image by using the convolutional neural network modelnUp-sampling to obtain size and characteristic image C4Consistent feature image Mn -；
S6 characteristic image C is processed by using convolution neural network modeln-1Performing convolution operation by 1 to obtain a characteristic image Cn-1 -；
S7 using convolution nerve network model to analyze the characteristic image Mn -And the characteristic image Cn-1 -Overlapping to obtain a characteristic image Mn-1；
S8 repeating the above steps S6-S7 to obtain the feature image Mn-2… characteristic image M2Characteristic image M1；
S9 using convolution neural network model to respectively process the characteristic images M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnPerforming convolution operation to make the characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels is the same;
the S10 convolutional neural network model adopts the sizes of [8 × 8, 16 × 16, 32 × 32, 64 × 64, 128 × 128 … 2 [ ]n+2*2n+2]n groups of prediction frames respectively predict characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnSmall target object in (1).
Preferably, the feature image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels is 256.
Preferably, n has a value of 5.
The small target object detection method provided by the embodiment of the invention has the following beneficial effects:
the method fully utilizes the characteristic images acquired in each convolution and downsampling process, superposes each characteristic with the characteristic output by downsampling next time, realizes the prediction of small target objects by using large-size characteristic images with less lost information, and predicts large target objects by using small-size characteristic images with more abstract semantic information obtained through multiple convolutions, so that the final prediction result is more accurate.
Drawings
Fig. 1 is a schematic flow chart of a small target object detection method according to an embodiment of the present invention;
fig. 2a to fig. 2d are schematic diagrams of effects obtained by using the method for detecting a small target object according to the embodiment of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
As shown in fig. 1, the method for detecting a small target object provided by the embodiment of the present invention includes the following steps:
s101, continuously and repeatedly carrying out down-sampling on an original image where a small target object is located by using a convolutional neural network model to obtain a plurality of characteristic images;
s102, sequencing a plurality of feature images by the convolutional neural network model according to the time sequence of the down sampling to obtain a feature image group;
s103, selecting the last n characteristic images in the characteristic image group by the convolutional neural network model, and sequentially marking the n characteristic images as C according to the size sequence1、C2、C3…Cn；
S104, utilizing the convolution neural network model to perform comparison on the characteristic image CnPerforming convolution operation by 1 to obtain a characteristic image Mn；
S105, performing M on the characteristic image by using the convolutional neural network modelnUp-sampling to obtain size and characteristic image C4Consistent feature image Mn -；
S106, using the convolution neural network model to perform characteristic image Cn-1Performing convolution operation by 1 to obtain a characteristic image Cn-1 -；
S107, utilizing the convolution neural network model to carry out feature image Mn -And the characteristic image Cn-1 -Overlapping to obtain a characteristic image Mn-1The fusion of information among different characteristic images is realized through pixel-by-pixel addition;
s108, repeating the steps S106-S107 to obtain the characteristic image Mn-2… characteristic image M2Characteristic image M1；
S109, respectively carrying out comparison on the characteristic images M by using the convolutional neural network model1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnPerforming convolution operation to make the characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels is the same;
s110, adopting the sizes of the convolutional neural network model as [8 × 8, 16 × 16, 32 × 32, 64 × 64, 128 × 128 … 2n +2*2n+2]n groups of prediction frames respectively predict characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnSmall target object in (1).
And (4) sliding the prediction frame on the characteristic image, classifying the result after each sliding, and realizing the detection on the small target object in the characteristic image.
Optionally, the characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels of (2) is 256.
Wherein the number of output channels is related to the parameters and the computing power of the convolutional neural network model.
Optionally, n has a value of 5.
Generally, the larger the value of n, the more accurate the final prediction result, but since up-sampling is performed once each time, the more the calculation amount is increased later, and therefore, 5 times are values that are preferably selected after being weighted between the accuracy and the calculation amount.
According to the small target object detection method provided by the embodiment of the invention, each feature is superposed with the feature output by the next downsampling by using the feature image acquired in each convolution and downsampling process, so that the small target object is predicted by using the large-size feature image with less lost information, the large target object is predicted by using the small-size feature image with more abstract semantic information obtained through multiple convolutions, and the accuracy of the prediction result is improved.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (4)
1. A small target object detection method, comprising:
s1, continuously and repeatedly carrying out down-sampling on the original image where the small target object is located to obtain a plurality of characteristic images;
s2, sequencing the plurality of feature images according to the time sequence of the down-sampling to obtain a feature image group;
s3, selecting the last n characteristic images in the characteristic image group, and sequentially recording the n characteristic images as the characteristic images according to the size sequenceC1、C2、C3…Cn；
S4 pairs of characteristic images CnPerforming convolution operation by 1 to obtain a characteristic image Mn；
S5 performing M on the characteristic imagenUp-sampling to obtain size and characteristic image C4Consistent feature image Mn -；
S6 pairs of characteristic images Cn-1Performing convolution operation by 1 to obtain a characteristic image Cn-1 -；
S7 feature image Mn -And the characteristic image Cn-1 -Overlapping to obtain a characteristic image Mn-1；
S8 repeating the steps S6-S7 to obtain the characteristic image Mn-2… characteristic image M2Characteristic image M1；
S9 corresponding to the feature image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnPerforming convolution operation to make the characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels is the same;
s10 adopts the size of [8 × 8, 16 × 16, 32 × 32, 64 × 64, 128 × 128 … 2 [ ]n+2*2n+2]n groups of prediction frames respectively predict characteristic image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnSmall target object in (1).
2. The small target object detection method according to claim 1, characterized in that the feature image M1Characteristic image M2Characteristic image M3… characteristic image Mn-1Characteristic image MnThe number of output channels is 256.
3. The small target object detection method according to claim 1, characterized in that the value of n is 5.
4. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of claims 1-2 are implemented when the computer program is executed by the processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010969487.XA CN112184641A (en) | 2020-09-15 | 2020-09-15 | Small target object detection method |
| CN202010969487X | 2020-09-15 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112581470A true CN112581470A (en) | 2021-03-30 |
Family
ID=73921231
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010969487.XA Withdrawn CN112184641A (en) | 2020-09-15 | 2020-09-15 | Small target object detection method |
| CN202011639587.2A Pending CN112581470A (en) | 2020-09-15 | 2020-12-31 | Small target object detection method |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010969487.XA Withdrawn CN112184641A (en) | 2020-09-15 | 2020-09-15 | Small target object detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112184641A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214505A (en) * | 2018-08-29 | 2019-01-15 | 中山大学 | A kind of full convolution object detection method of intensive connection convolutional neural networks |
| CN110163057A (en) * | 2018-10-29 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Object detection method, device, equipment and computer-readable medium |
| WO2019201035A1 (en) * | 2018-04-16 | 2019-10-24 | 腾讯科技（深圳）有限公司 | Method and device for identifying object node in image, terminal and computer readable storage medium |
| CN110796640A (en) * | 2019-09-29 | 2020-02-14 | 郑州金惠计算机系统工程有限公司 | Small target defect detection method and device, electronic equipment and storage medium |
| CN111222474A (en) * | 2020-01-09 | 2020-06-02 | 电子科技大学 | Method for detecting small target of high-resolution image with any scale |
-
2020
- 2020-09-15 CN CN202010969487.XA patent/CN112184641A/en not_active Withdrawn
- 2020-12-31 CN CN202011639587.2A patent/CN112581470A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019201035A1 (en) * | 2018-04-16 | 2019-10-24 | 腾讯科技（深圳）有限公司 | Method and device for identifying object node in image, terminal and computer readable storage medium |
| CN109214505A (en) * | 2018-08-29 | 2019-01-15 | 中山大学 | A kind of full convolution object detection method of intensive connection convolutional neural networks |
| CN110163057A (en) * | 2018-10-29 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Object detection method, device, equipment and computer-readable medium |
| CN110796640A (en) * | 2019-09-29 | 2020-02-14 | 郑州金惠计算机系统工程有限公司 | Small target defect detection method and device, electronic equipment and storage medium |
| CN111222474A (en) * | 2020-01-09 | 2020-06-02 | 电子科技大学 | Method for detecting small target of high-resolution image with any scale |
Non-Patent Citations (1)
| Title |
|---|
| TSUNG-YI LIN ET AL: "Feature Pyramid Networks for Object Detection", 《 2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112184641A (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3066029A1 (en) | Image feature acquisition | |
| CN110310253B (en) | Digital slice classification method and device | |
| CN111444394A (en) | Method, system and equipment for obtaining relation expression between entities and advertisement recalling system | |
| CN111523546A (en) | Image semantic segmentation method, system and computer storage medium | |
| CN110827297A (en) | Insulator segmentation method for generating countermeasure network based on improved conditions | |
| US11619593B2 (en) | Methods and systems for detecting a defect of a film | |
| CN111563507A (en) | Indoor scene semantic segmentation method based on convolutional neural network | |
| CN106779055B (en) | Image characteristic extracting method and device | |
| CN112800955A (en) | Remote sensing image rotating target detection method and system based on weighted bidirectional feature pyramid | |
| CN115471448A (en) | Artificial intelligence-based thymus tumor histopathology typing method and device | |
| CN114821102A (en) | Intensive citrus quantity detection method, equipment, storage medium and device | |
| CN116071352A (en) | Method for generating surface defect image of electric power safety tool | |
| CN111832479B (en) | Video target detection method based on improved self-adaptive anchor point R-CNN | |
| CN113345052A (en) | Classified data multi-view visualization coloring method and system based on similarity significance | |
| CN112581470A (en) | Small target object detection method | |
| CN117058235A (en) | Visual positioning method crossing various indoor scenes | |
| CN111723742A (en) | Crowd density analysis method, system and device and computer readable storage medium | |
| CN115564954A (en) | Chromosome image segmentation method | |
| CN115984547A (en) | Target detection model, training method and system, and target detection method and system | |
| CN112925994B (en) | Group recommendation method, system and equipment based on local and global information fusion | |
| CN113313030B (en) | Human behavior identification method based on motion trend characteristics | |
| CN115410047A (en) | Infrared image electric bicycle target detection method based on improved YOLO v5s | |
| CN114863094A (en) | Industrial image region-of-interest segmentation algorithm based on double-branch network | |
| CN115424012A (en) | Lightweight image semantic segmentation method based on context information | |
| CN114529794A (en) | Infrared and visible light image fusion method, system and medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210517 Address after: 100025 6th floor, main building, No.3 yanjingli middle street, Chaoyang District, Beijing Applicant after: CHINA TEXTILE ENGINEERING SOCIETY Applicant after: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE Co.,Ltd. Applicant after: Guangzhou guantu Vision Technology Co.,Ltd. Address before: 528200 1st, 3rd and 4th floor, South Technology Innovation Center, Xiqiao Textile City, Nanhai District, Foshan City, Guangdong Province Applicant before: FOSHAN ZHONGFANGLIAN INSPECTION TECHNOLOGY SERVICE Co.,Ltd. Applicant before: Guangzhou guantu Vision Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210330 |