Abstract
This paper proposes an image augmentation model of limited samples on the mobile platform for object tracking. The augmentation method mainly aims at the detection failure caused by the small number of effective samples, jitter of tracking platform, and relative rotation between camera and object in the tracking process. Aiming at the object tracking problem, we first propose to use geometric projection transformation, multi-directional overlay blurring, and random background filling to improve the generalization ability of samples. Then, selecting suitable traditional augmentation methods as the supplements, an image augmentation model with an adjustable probability factor is provided to simulate various kinds of samples to help the detection model carry out more reliable training. Finally, combined with a spatial localization algorithm based on geometric constraints proposed by the author’s previous work, a framework for object tracking with an image augmentation method is proposed. SSD, YOLOv3, YOLOv4, and YOLOx are adopted in the experiment of this paper as the detection models. And a large number of object recognition and object tracking experiments are carried out by combining with common data sets OTB50 and OTB100 as well as the OTMP data set proposed by us for mobile platform. The augmented module proposed in this paper is conducive for the detection model to improve the detection accuracy by at least 10%. Especially for objects with planar characteristics, the affine and projection transformation used in this paper can greatly improve the detection accuracy of the model. Based on the object tracking framework of our augmented model, the RMSE is estimated to be less than 4.21 cm in terms of the actual tracking of indoor objects.
Highlights
Padding Flip/Crop Probability FactorBrightness Adjustment Gaussian Noise Color Jittering BlurringAugmented SamplesFrameworkofofLimited LimitedSamples
An Image Augmentation Method Based on Limited Samples for Object Tracking based on the Mobile Platform is proposed in this paper to achieve effective tracking of the frame moving objects
Our method is aiming at solving the problem of the insufficient generalization ability of neural networks when training a small number of samples under the background of object tracking
Summary
With the rapid development of deep learning theory in the field of computer vision, image data samples, as one of the key core driving forces in various learning models, play a decisive role in neural network model training. The function is to expand the number of sample sets that can be trained by the network and improve the model generalization ability. Based on the above consideration, we propose a data augmentation method for a small sample set, which can be used to deal with 3D object tracking tasks on the moving platform. Based on the two augmentation methods in part 1, combined with traditional augmentation methods such as geometric augmentation, brightness adjustment, Gaussian noise injection, and color jittering, an image augmentation model is proposed to deal with the problem of object tracking in insufficient samples.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have