Night multi-target tracking method and system based on domain adaptive learning

Abstract

The invention belongs to the technical field of computer vision, and provides a night multi-target tracking method and system based on domain adaptive learning, and the method comprises the steps: obtaining daytime image data and night image data; performing image conversion processing on the acquired daytime image data to obtain a night conversion image; according to the night image data, the night conversion image and the domain adaptive learning model, performing a night multi-target tracking task to complete multi-target tracking of the night environment; wherein the domain adaptive learning model adopts a teacher-student network, a tracking result is obtained according to the teacher network and the night image data, and the obtained tracking result is used as a pseudo tag; and guiding the student network to carry out unsupervised learning on the night image data based on the pseudo tag, carrying out supervised learning on the night conversion image by the student network, and guiding student network training according to the multi-domain learning loss value of the student network to obtain a domain adaptive learning model.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer vision, and in particular relates to a method and system for nighttime multi-target tracking based on domain adaptive learning. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the development of deep learning, neural network technology is applied in more and more scenarios, and multi-target tracking has attracted more and more attention in the field of computer vision due to its wide application in video surveillance, unmanned driving and intelligent transportation; its main purpose is to accurately track multiple moving targets in a video sequence and maintain their identity consistency. With the continuous advancement of convolutional neural network target detection technology, detection-based tracking algorithms have now become the mainstream direction in the field of multi-target tracking. Targets are identified in each frame through target detection, and these detection results are used for data association to establish the trajectory of the target in the video sequence.

[0004] Existing multi-target tracking methods are mainly developed for daytime data, which leads to relatively poor multi-target tracking performance in nighttime environments. Due to the difficulty of data collection in nighttime environments, the high cost and the complexity of labeling work, labeled nighttime datasets are very scarce; the lack of sufficient quantity and quality of labeled nighttime datasets limits the performance improvement of multi-target tracking algorithms in nighttime environments. There are large differences between daytime environments and nighttime environments. For example, changes in factors such as illumination, shadows, and reflections lead to large differences in brightness and contrast. Since there are few labeled nighttime data, supervised learning methods are difficult to implement. Supervised learning methods are prone to overfitting, which makes it difficult to improve the performance of the algorithm. Therefore, how to process nighttime datasets and occluded targets has become a major problem that needs to be solved urgently.

[0005] Existing multi-target tracking relies on a large amount of labeled data for supervised learning, but in new unlabeled data scenarios, the performance often drops significantly; the multi-target tracking method that can use unsupervised domain adaptive learning uses pseudo labels to significantly improve the performance of new scenarios. The multi-target tracking network is constructed using a feature extractor, a detection branch, an identity embedding branch, and a context prediction branch. The network is used to obtain pseudo labels for data in new scenarios, and an identity aggregation module is combined to correct the pseudo labels. The pseudo labels are combined with the context prediction branch to train the entire multi-target tracking network, and the network with updated parameters is used to track multiple targets in new scenarios; this method can effectively improve the tracking performance in unlabeled scenarios, but it is mainly used in daytime scenes, such as campuses, squares, and roads, ignoring the impact of illumination changes between different scenes. Therefore, the performance is still poor in nighttime scenes with insufficient illumination, less color information, and low contrast. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method and system for nighttime multi-target tracking based on domain adaptive learning. By performing image conversion on daytime data to simulate the nighttime environment, guiding the student network based on the teacher network, and learning the nighttime data features in an unsupervised domain adaptive manner, the nighttime multi-target tracking is realized, so as to solve the problem of inaccurate nighttime data tracking in the multi-target tracking problem and improve the multi-target tracking performance in the nighttime environment.

[0007] According to some embodiments, a first solution of the present invention provides a nighttime multi-target tracking method based on domain adaptive learning, which adopts the following technical solutions:

[0008] A nighttime multi-target tracking method based on domain adaptive learning, comprising:

[0009] Acquire daytime image data and nighttime image data;

[0010] Performing image conversion processing on the acquired daytime image data to obtain a nighttime conversion image;

[0011] Based on night image data, night conversion images and domain adaptive learning models, night multi-target tracking tasks are carried out to complete multi-target tracking in night environments;

[0012] Among them, the domain adaptive learning model adopts a teacher-student network, obtains tracking results based on the teacher network and night image data, and uses the obtained tracking results as pseudo labels; based on the pseudo labels, the student network is guided to perform unsupervised learning on the night image data, and the student network performs supervised learning on the night conversion images. The student network training is guided according to the multi-domain learning loss value of the student network to obtain a domain adaptive learning model.

[0013] As a further technical limitation, night image data is input into the teacher network for image target tracking, the obtained preliminary results of image target tracking are filtered by a confidence threshold, the preliminary results of image target tracking exceeding the confidence threshold are used as tracking results, and the tracking results obtained by the teacher network are used to guide the pseudo-label training of the student network; the obtained tracking results are related to the weight value of the teacher network, and the teacher network weight can be obtained by an exponential moving average.

[0014] As a further technical limitation, unsupervised learning of the night image data by the student network is performed based on the obtained pseudo-labels to obtain an unsupervised learning loss value.

[0015] Furthermore, the night conversion image is input into the student network for supervised learning of the image to obtain a supervised learning loss value; the obtained unsupervised learning loss value and supervised learning loss value are used to obtain a multi-domain learning loss value, and multiple rounds of student network training are performed according to the multi-domain learning loss value. When the multi-domain learning loss value is minimized, a domain adaptive learning model is obtained; based on the student network weight value obtained in each round of training, the exponential moving average is used to update the weight value of the teacher network.

[0016] As a further technical limitation, in the process of nighttime multi-target tracking, the acquired nighttime image data is input into the obtained domain adaptive model, and the output result of the domain adaptive model is the target tracking trajectory of the nighttime scene, thereby obtaining the nighttime multi-target tracking result.

[0017] As a further technical limitation, the image conversion process at least includes image brightness adjustment, image contrast adjustment, image Gaussian noise removal and image Gaussian blur enhancement.

[0018] According to some embodiments, a second solution of the present invention provides a nighttime multi-target tracking system based on domain adaptive learning, which adopts the following technical solutions:

[0019] A nighttime multi-target tracking system based on domain adaptive learning, comprising:

[0020] An acquisition module configured to acquire daytime image data and nighttime image data;

[0021] A conversion module, which is configured to perform image conversion processing on the acquired daytime image data to obtain a nighttime conversion image;

[0022] A tracking module is configured to perform a nighttime multi-target tracking task based on nighttime image data, nighttime conversion images, and a domain adaptive learning model to complete multi-target tracking in a nighttime environment;

[0023] Among them, in the tracking module, the domain adaptive learning model adopts a teacher-student network, obtains the tracking results according to the teacher network and the night image data, and uses the obtained tracking results as pseudo labels; based on the pseudo labels, the student network is guided to perform unsupervised learning on the night image data, and the student network performs supervised learning on the night conversion images. The student network training is guided according to the multi-domain learning loss value of the student network to obtain the domain adaptive learning model.

[0024] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution:

[0025] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of the nighttime multi-target tracking method based on domain adaptive learning as described in the first solution of the present invention.

[0026] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution:

[0027] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in the method for nighttime multi-target tracking based on domain adaptive learning as described in the first solution of the present invention are implemented.

[0028] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution:

[0029] A computer program product includes software codes, wherein the program in the software codes executes the steps in the method for nighttime multi-target tracking based on domain adaptive learning as described in the first solution of the present invention.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] This embodiment simulates the night environment through daytime image data and performs supervised training of the domain adaptive learning model, which can effectively learn the data distribution of the night environment, make full use of labeled daytime data sets and unlabeled nighttime data sets to train the domain adaptive learning model, and improve the performance of nighttime multi-target tracking while reducing the cost of nighttime data annotation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0033] Figure 1 This is a basic flow chart of the nighttime multi-target tracking method based on domain adaptive learning in Embodiment 1 of the present invention;

[0034] Figure 2 This is a schematic diagram of training a domain adaptive learning model in Embodiment 1 of the present invention;

[0035] Figure 3 This is an architecture diagram of the nighttime multi-target tracking method based on domain adaptive learning in Example 1 of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0039] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0040] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they cannot be understood as limitations on the present invention.

[0041] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0042] Embodiment 1

[0043] Embodiment 1 of the present invention introduces a nighttime multi-target tracking method based on domain adaptive learning.

[0044] like Figure 1A nighttime multi-target tracking method based on domain adaptive learning is shown, which trains a domain adaptive learning model based on a labeled daytime data set (in this embodiment, the domain adaptive learning model adopts a multi-target tracking network), and then applies the trained multi-target tracking network to the nighttime data set to obtain the target tracking trajectory in the nighttime scene.

[0045] In order to realize multi-target tracking at night, this embodiment realizes multi-target tracking at night through a trained multi-target tracking network; the training process of the multi-target tracking network is as follows: Figure 2 As shown, the overall process steps are:

[0046] (1) Given a labeled daytime dataset and an unlabeled nighttime dataset, the multi-target tracking network is first trained using the daytime dataset to obtain the initialized multi-target tracking network weight parameters, and the teacher-student model is constructed using the initialized multi-target tracking network.

[0047] (2) Perform image conversion processing on the daytime dataset by random brightness, contrast, Gaussian noise, and Gaussian blur enhancement to obtain a labeled dataset with similar characteristics to the nighttime images;

[0048] (3) Inputting the image conversion processed dataset and the night dataset into the student network to obtain the tracking results; inputting the night dataset into the teacher network to obtain the tracking results, and filtering the tracking results through the confidence threshold to obtain high-confidence tracking results as pseudo labels to guide the training of the student model;

[0049] (4) The tracking result of the converted dataset output by the student network directly uses the label of the daytime dataset to calculate the loss value of supervised learning. The supervised loss is calculated based on the result output by the student network and the label of the daytime dataset:

[0050]

[0051] in, represents the classification loss, that is, the loss of the i-th anchor box being classified as the j-th true box category, represents the regression loss, that is, the loss of the i-th anchor box regressing to the j-th real box in terms of attributes such as position and size. λ represents a hyperparameter used to adjust the weight between classification loss and regression loss.

[0052]

[0053] L reg = -log(IoU(B gt ,B pred ))

[0054] Where n represents the total number of samples, i represents the index of the sample, representing the i-th sample, and t i Represents the true label of the i-th sample, usually taking the value of 0 or 1, used to indicate the true category of the sample, p i represents the probability that the model predicts that the i-th sample is a positive class (such as class 1), B gt represents the ground-truth bounding box, B pred It represents the predicted bounding box, IoU represents the intersection ratio, and calculates the degree of overlap between the real box and the predicted box.

[0055] The output nighttime data set tracking results use the pseudo labels obtained by the teacher model to calculate the loss value of unsupervised learning. The teacher network is used to guide the student network. The unsupervised loss is calculated as follows:

[0056]

[0057] Where KL represents the KL divergence function, represents the target category predicted by the teacher network, I t Represents the picture of the night dataset, C student represents the target category predicted by the student network.

[0058] The loss values ​​of supervised learning and unsupervised learning are used to guide the student network training, and the weight parameters of the teacher network are updated by the exponential moving average method. The update formula of the exponential moving average method is as follows:

[0059]

[0060] in, represents the teacher network parameter after the tth update, α is the smoothing factor, which usually takes a smaller value, and represents the weight of the new parameter update, θ t represents the student network parameters after the tth update, Represents the teacher network parameters after the previous update.

[0061] (5) Repeat the above steps (3) and (4) until the specified number of training rounds is reached.

[0062] This embodiment adopts Figure 2 The architecture diagram shown includes three modules: daytime image conversion, domain adaptive learning, and loss calculation. The input data of this embodiment includes a nighttime data set and a daytime data set for image conversion processing. After the input data, domain adaptive learning and loss calculation are performed to obtain the weight parameters of the multi-target tracking network in the nighttime environment, and then the nighttime multi-target tracking task is performed to obtain the tracking trajectory of the target in the nighttime environment.

[0063] As one or more implementation modes, the obtained daytime data set is subjected to image conversion processing, and the image conversion processing at least includes image brightness adjustment, image contrast adjustment, image Gaussian noise removal and image Gaussian blur enhancement; the data characteristics of nighttime images are simulated by the obtained image conversion data, so that the multi-target tracking network training in domain adaptive learning is more robust.

[0064] As one or more implementation methods, the domain adaptive learning module uses a teacher-student network to train a multi-target tracking network in a night environment, wherein the student network is mainly used for multi-domain training on a daytime dataset that has undergone image conversion and an unlabeled nighttime dataset, and the teacher network is used to generate pseudo labels on an unlabeled nighttime dataset and provide them to the student model, and the weights are obtained by the student model through an exponential moving average method EMA. In order to generate more reliable pseudo labels, the tracking results output by the teacher network are filtered by a confidence threshold to obtain high-confidence tracking results as the final pseudo labels to guide the training of the student network.

[0065] As one or more implementation methods, the calculated loss includes supervised learning and unsupervised learning; supervised learning is performed on the data obtained after the image conversion process, the loss value between the tracking result and the label is calculated, and the unsupervised loss result obtained by the student network under the guidance of the teacher network pseudo-label is calculated. According to the calculated loss value, the parameters are continuously adjusted to train the multi-target tracking network so that the tracking result is as close to the real result as possible.

[0066] As one or more implementation modes, during the process of nighttime multi-target tracking, the acquired nighttime image data is input into the obtained domain adaptive model, and the output result of the domain adaptive model is the target tracking trajectory of the nighttime scene, thereby obtaining the nighttime multi-target tracking result.

[0067] Due to the large difference between daytime data and nighttime data, the performance of the multi-target tracking network trained on the labeled daytime dataset will be greatly reduced if it is directly applied to the nighttime environment. Therefore, this embodiment adds two processes, image conversion processing and domain adaptive learning, to first perform image conversion processing on the labeled daytime dataset to simulate the nighttime environment. Since there is a large gap between night data and day data in terms of illumination, color information, contrast, image noise, etc., and the night data set lacks label information, only using the day data set to train the multi-target tracking network cannot achieve good results in the night environment; using the day data set after image conversion processing can better simulate the characteristics of night images and extract the robustness features of the night environment and targets; after the image conversion processing is completed, the teacher-student model is used in domain adaptive learning to train the multi-target tracking network. The student network in the teacher-student model uses the labeled day data set and the unlabeled night data set after image conversion processing as input, while the teacher network only uses the night data set as input to generate pseudo labels to guide the student network; in domain adaptive learning, the teacher-student model is used to supervise the day data after conversion processing, and unsupervised learning is performed on the unlabeled night data, so that all day and night data can be fully utilized to train the multi-target tracking network, effectively solving the distribution difference between day and night data, thereby improving the multi-target tracking performance in the night environment.

[0068] This embodiment is based on the simulation of nighttime data converted from daytime images. The daytime dataset is processed by random brightness, contrast, Gaussian noise, and Gaussian blur enhancement to obtain a labeled dataset with similar characteristics to nighttime images. The teacher-student model is used for unsupervised domain adaptive learning to improve the tracking performance of the multi-target tracking network in an unlabeled nighttime dataset.

[0069] This embodiment performs image conversion processing on the daytime dataset, so that the daytime dataset can simulate the nighttime environment more accurately. By using this dataset simulating the nighttime environment instead of the original daytime dataset for supervised training of the multi-target tracking network, the data distribution of the nighttime environment can be effectively learned. At the same time, in order to make full use of a large amount of unlabeled nighttime data, this embodiment uses a teacher-student model for unsupervised domain adaptive learning, wherein the teacher network takes the unlabeled nighttime dataset as input, filters the output tracking results through a confidence threshold, and obtains the filtered high-confidence results as pseudo-labels to guide the student network for unsupervised learning. The entire domain adaptive learning process makes full use of the labeled daytime dataset and the unlabeled nighttime dataset to train the multi-target tracking network, thereby improving the performance of multi-target tracking at night while reducing the cost of nighttime data annotation.

[0070] Embodiment 2

[0071] Embodiment 2 of the present invention introduces a nighttime multi-target tracking system based on domain adaptive learning.

[0072] A nighttime multi-target tracking system based on domain adaptive learning, comprising:

[0073] An acquisition module configured to acquire daytime image data and nighttime image data;

[0074] A conversion module, which is configured to perform image conversion processing on the acquired daytime image data to obtain a nighttime conversion image;

[0075] A tracking module is configured to perform a nighttime multi-target tracking task based on nighttime image data, nighttime conversion images, and a domain adaptive learning model to complete multi-target tracking in a nighttime environment;

[0076] Among them, in the tracking module, the domain adaptive learning model adopts a teacher-student network, obtains the tracking results according to the teacher network and the night image data, and uses the obtained tracking results as pseudo labels; based on the pseudo labels, the student network is guided to perform unsupervised learning on the night image data, and the student network performs supervised learning on the night conversion images. The student network training is guided according to the multi-domain learning loss value of the student network to obtain the domain adaptive learning model.

[0077] The detailed steps are the same as those of the nighttime multi-target tracking method based on domain adaptive learning provided in Example 1, and will not be repeated here.

[0078] Embodiment 3

[0079] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0080] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps in the nighttime multi-target tracking method based on domain adaptive learning as described in Embodiment 1 of the present invention.

[0081] The detailed steps are the same as those of the nighttime multi-target tracking method based on domain adaptive learning provided in Example 1, and will not be repeated here.

[0082] Embodiment 4

[0083] A fourth embodiment of the present invention provides an electronic device.

[0084] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in the method for nighttime multi-target tracking based on domain adaptive learning as described in Embodiment 1 of the present invention are implemented.

[0085] The detailed steps are the same as those of the nighttime multi-target tracking method based on domain adaptive learning provided in Example 1, and will not be repeated here.

[0086] Embodiment 5

[0087] Embodiment 5 of the present invention provides a computer program product.

[0088] A computer program product includes software code, wherein the program in the software code executes the steps in the method for nighttime multi-target tracking based on domain adaptive learning as described in Embodiment 1 of the present invention.

[0089] The detailed steps are the same as those of the nighttime multi-target tracking method based on domain adaptive learning provided in Example 1, and will not be repeated here.

[0090] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A nighttime multi-target tracking method based on domain adaptive learning, characterized in that: include: Acquire daytime image data and nighttime image data; Performing image conversion processing on the acquired daytime image data to obtain a nighttime conversion image; Based on night image data, night conversion images and domain adaptive learning models, night multi-target tracking tasks are carried out to complete multi-target tracking in night environments; Among them, the domain adaptive learning model adopts a teacher-student network, obtains tracking results based on the teacher network and night image data, and uses the obtained tracking results as pseudo labels; based on the pseudo labels, the student network is guided to perform unsupervised learning on the night image data, and the student network performs supervised learning on the night conversion images. The student network training is guided according to the multi-domain learning loss value of the student network to obtain a domain adaptive learning model.

2. A method for tracking multiple targets at night based on domain adaptive learning as claimed in claim 1, characterized in that: The night image data is input into the teacher network for image target tracking, the preliminary image target tracking results obtained are filtered by the confidence threshold, and the preliminary image target tracking results exceeding the confidence threshold are used as tracking results. The tracking results obtained by the teacher network are used to guide the pseudo-label training of the student network. The obtained tracking results are related to the weight values ​​of the teacher network, and the teacher network weights can be obtained by exponential moving average.

3. A method for tracking multiple targets at night based on domain adaptive learning as claimed in claim 1, characterized in that: According to the obtained pseudo labels, the student network performs unsupervised learning on the night image data to obtain the unsupervised learning loss value.

4. A method for tracking multiple targets at night based on domain adaptive learning as claimed in claim 3, characterized in that: The night conversion image is input into the student network for supervised learning of the image to obtain the supervised learning loss value; the obtained unsupervised learning loss value and supervised learning loss value are used to obtain the multi-domain learning loss value, and the student network is trained multiple rounds according to the multi-domain learning loss value. When the multi-domain learning loss value is minimized, the domain adaptive learning model is obtained; according to the student network weight value obtained in each round of training, the exponential moving average is used to update the weight value of the teacher network.

5. A method for nighttime multi-target tracking based on domain adaptive learning as claimed in claim 1, characterized in that: In the process of nighttime multi-target tracking, the acquired nighttime image data is input into the obtained domain adaptive model, and the output result of the domain adaptive model is the target tracking trajectory of the nighttime scene, thereby obtaining the nighttime multi-target tracking result.

6. A method for nighttime multi-target tracking based on domain adaptive learning as claimed in claim 1, characterized in that: The image conversion process at least includes image brightness adjustment, image contrast adjustment, image Gaussian noise removal and image Gaussian blur enhancement.

7. A nighttime multi-target tracking system based on domain adaptive learning, characterized in that: include: An acquisition module configured to acquire daytime image data and nighttime image data; A conversion module, which is configured to perform image conversion processing on the acquired daytime image data to obtain a nighttime conversion image; A tracking module is configured to perform a nighttime multi-target tracking task based on nighttime image data, nighttime conversion images, and a domain adaptive learning model to complete multi-target tracking in a nighttime environment; Among them, in the tracking module, the domain adaptive learning model adopts a teacher-student network, obtains the tracking results according to the teacher network and the night image data, and uses the obtained tracking results as pseudo labels; based on the pseudo labels, the student network is guided to perform unsupervised learning on the night image data, and the student network performs supervised learning on the night conversion images. The student network training is guided according to the multi-domain learning loss value of the student network to obtain the domain adaptive learning model.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the nighttime multi-target tracking method based on domain adaptive learning as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the nighttime multi-target tracking method based on domain adaptive learning are implemented as described in any one of claims 1-6.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the nighttime multi-target tracking method based on domain adaptive learning as described in any one of claims 1 to 6.

Images