Search

In order to achieve infrared aircraft detection under interference conditions, this paper proposes an infrared aircraft detection algorithm based on high-resolution feature-enhanced semantic segmentation network. Firstly, the designed location attention mechanism is utilized to enhance the current-level feature map by obtaining correlation weights between pixels at different positions. Then, it is fused with the high-level feature map rich in semantic features to construct a location attention feature fusion network, thereby enhancing the representation capability of target features. Secondly, based on the idea of using dilated convolutions to expand the receptive field of feature maps, a hybrid atrous spatial pyramid pooling module is designed. By utilizing a serial structure of dilated convolutions with small dilation rates, this module addresses the issue of feature information loss when expanding the receptive field through dilated spatial pyramid pooling. It captures the contextual information of the target, further enhancing the target features. Finally, a dice loss function is introduced to calculate the overlap between the predicted results and the ground truth labels, facilitating deep excavation of foreground information for comprehensive learning of samples. This paper constructs an infrared aircraft detection algorithm based on a high-resolution feature-enhanced semantic segmentation network which combines the location attention feature fusion network, the hybrid atrous spatial pyramid pooling module, the dice loss function, and a network that maintains the resolution of feature maps. Experiments conducted on a self-built infrared dataset show that the proposed algorithm achieves a mean intersection over union (mIoU) of 92.74%, a mean pixel accuracy (mPA) of 96.34%, and a mean recall (MR) of 96.19%, all of which outperform classic segmentation algorithms such as DeepLabv3+, Segformer, HRNetv2, and DDRNet. This demonstrates that the proposed algorithm can achieve effective detection of infrared aircraft in the presence of interference. [ABSTRACT FROM AUTHOR]

Aiming at the energy inconsistency of each battery during the use of lithium‐ion batteries (LIBs), a bidirectional active equalization topology of lithium battery packs based on energy transfer was constructed, and a bivariate equalization control strategy of adjacent SOC difference and voltage is proposed according to the corresponding relationship between open circuit voltage (OCV) and state of charge (SOC). The energy transfer between the inductor and the lithium battery is realized through the combination of the main circuit and the secondary circuit. Based on the Buck–Boost equalization circuit, the pulse width modulation (PWM) drive signal duty ratio is adjusted to improve the equalization speed and efficiency. The SOC is estimated by the unscented Kalman filter (UKF) algorithm, and the SOC of each single battery is estimated and sorted. The results of charge and discharge and static simulation and test of lithium battery show that the SOC difference between each cell is controlled within the threshold value of 3%, the voltage range is controlled within the range of 0.01 V, and the equalization speed is increased by 51% compared with the traditional unidirectional transfer of inductive energy balancing method. The change trend of the test results and the simulation results show a good consistency, avoiding the overcharge and overdischarge of the battery pack, and reducing the inconsistency. This method can complete the energy balance management of the battery well, the efficiency is relatively high, and the service life of the battery is improved. [ABSTRACT FROM AUTHOR]

To address the issue of insufficient extraction of target features and the resulting impact on detection performance in long-range infrared aircraft target detection caused by small imaging area and weak radiation intensity starting from the idea of perceiving target context to enhance the features extracted by convolutional neural network, this paper proposes a detecting algorithm based on AWFGLC (adaptive weighted fusion of global–local context). Based on the mechanism of AWFGLC, the input feature map is randomly reorganized and partitioned along the channel dimension, resulting in two feature maps. One feature map is utilized by self-attention for global context modeling, establishing the correlation between target features and background features to highlight the salient features of the target, thereby enabling the detecting algorithm to better perceive the global features of the target. The other feature map is subjected to window partitioning, with max pooling and average pooling performed within each window to highlight the local features of the target. Subsequently, self-attention is applied to the pooled feature map for local context modeling, establishing the correlation between the target and its surrounding neighborhood, further enhancing the weaker parts of the target features, and enabling the detecting algorithm to better perceive the local features of the target. Based on the characteristics of the target, an adaptive weighted fusion strategy with learnable parameters is employed to aggregate the global context and local context feature maps. This results in a feature map containing more complete target information, enhancing the ability of the detection algorithm to distinguish between target and background. Finally, this paper integrates the mechanism of AWFGLC into YOLOv7 for the detection of infrared aircraft targets. The experiments indicate that the proposed algorithm achieves mAP50 scores of 97.8% and 88.7% on self-made and publicly available infrared aircraft datasets, respectively. Moreover, the mAP50:95 scores reach 65.7% and 61.2%, respectively. These results outperform those of classical target detection algorithms, indicating the effective realization of infrared aircraft target detection. [ABSTRACT FROM AUTHOR]

Weakly supervised object detection (WSOD) is becoming increasingly important for computer vision tasks, as it alleviates the burden of manual annotation. Most WSOD techniques rely on multiple instance learning (MIL), which tends to localise the discriminative parts of salient objects instead of the whole object. In addition, network training is often supervised using simple image‐level annotations, without including object quantities or location information. However, this can lead to ambiguous differentiation of object instances, both in terms of location and semantics. To address these issues, propose an end‐to‐end triple critical feature capture network (TCFCNet) for WSOD is proposed. Specifically, a multi‐task branch, which can perform fully supervised classification and regression task, was integrated with a PCL in an end‐to‐end network for refining object locations in an online method. A cyclic parametric dropblock module (CPDM) was then designed to help the detector focus on the contextual information by using cyclic masking techniques to maximise the removal of the discriminative components of an object instance to alleviate the part domination problem. Finally, a feature decoupling module (FDM) is proposed to further reduce the ambiguous distinction of object instances by adaptively constructing robust critical features that adapt to multi‐task branch for classification and regression tasks, which contains a feature enhancement module and task‐specific polarisation functions. Comprehensive experiments are carried out on the challenging Pascal VOC 2007 and VOC 2012 datasets. The proposed method achieves a 54.6% mAP and a 44.3% mAP on the Pascal VOC 2007 and VOC 2012 datasets respectively, showed that our method outperformed existing mainstream techniques by a considerable margin. [ABSTRACT FROM AUTHOR]

In off-axis quantitative phase imaging, existing methods of suppressing the zero-frequency component (ZFC) always cause the loss of high-frequency phase information, thus degrading the accuracy of phase reconstruction. To overcome these problems, this paper proposes to preserve the high-frequency information by filtering the intrinsic mode function. In this method, empirical mode decomposition is employed to decompose the interferometric image into a series of intrinsic mode function (IMF) components from high to low frequencies. The decomposed low-frequency IMF components are processed by Gaussian high-pass filters for ZFC suppression, and the high-frequency IMF components and the filtered low-frequency IMF components are combined to obtain the reconstructed hologram. Hilbert transform is then performed on the reconstructed hologram to filter out the conjugate image, leaving only the original image. In order to verify the performance of our proposed method, the phase maps processed by our proposed method are compared with those processed by the Fourier filtering method, wavelet transform-based method and Laplace operator method. The experimental results show that the proposed method not only suppresses ZFC but also achieves higher accuracy in phase reconstruction. [ABSTRACT FROM AUTHOR]

In three-dimensional (3D) shape measurement based on fringe projection, various factors can degrade the quality of the point cloud. Existing point cloud filtering methods involve analyzing the geometric relationship between 3D space and point cloud, which poses challenges such as complex calculation and low efficiency. To improve the accuracy and speed of point cloud filtering, this paper proposes a new point cloud filtering method based on image segmentation and the absolute phase for the 3D imaging obtained by fringe projection. Firstly, a two-dimensional (2D) point cloud mapping image is established based on the 3D point cloud obtained from fringe projection. Secondly, threshold segmentation and region growing methods are used to segment the 2D point cloud mapping image, followed by recording and removal of the segmented noise region. Using the relationship between the noise point cloud and the absolute phase noise point in fringe projection, a reference noise-free point is established, and the absolute phase line segment is restored to obtain the absolute phase of the noise-free point. Finally, a new 2D point cloud mapping image is reconstructed in 3D space to obtain a point cloud with noise removed. Experimental results show that the point cloud denoising accuracy calculated by this method can reach up to 99.974%, and the running time is 0.954 s. The proposed method can effectively remove point cloud noise and avoid complex calculations in 3D space. This method can not only remove the noise of the 3D point cloud but also can restore the partly removed noise point cloud into a noise-free 3D point cloud, which can improve the accuracy of the 3D point cloud. [ABSTRACT FROM AUTHOR]

Hadamard single-pixel imaging (SPI) employs the differential measurement strategy to eliminate the effect of negative value of Hadamard basis patterns but leads to doubling the number of measurements. To reduce the number of measurements, a Hadamard SPI method based on positive patterns is proposed. In this method, only the positive patterns are used to acquire measurement values and reconstruct images, so the number of measurements will be reduced by 1/2. Combined with the intensity correlation theory of ghost imaging, the average value of the acquired measures is found; this average value is subtracted from all the measurement values to obtain the spectral coefficients, thus the background noise is eliminated to ensure the imaging quality. Simulation and experimental results show that the proposed method has good noise robustness and can efficiently reconstruct high quality images. [ABSTRACT FROM AUTHOR]

We present a novel neural network signal calibration technique to improve the performance of triangulation-based structured light profilometers based on digital projection. The performance of such profilometers is often hindered by the capture of aberrated pattern intensity distributions, and hence we address this problem by employing neural networks in a signal mapping approach. We exploit the generalization and interpolation capabilities of a feed-forward backpropagation neural network to map from distorted fringe data to nondistorted data. The performance of the calibration technique is gauged both through simulation and experimentation, with simulation results indicating that accuracy can be improved by more than 80%. The technique requires just one image cross section for calibration and hence is ideal for rapid profiling applications. OCIS codes: 120.6650, 120.2650, 150.6910.

What is believed to be a new analysis algorithm to carry out profile measurement with low computational complexity and less noise sensitivity is presented. First, a discrete cosine transform (DCT)-based representation method is introduced to express the height distribution of a 3D surface. Then a novel shift estimation algorithm, called the DCT-based shift estimation (DCT-SE), is presented to reconstruct 3D object surfaces by using the proposed expression and the generalized analysis model. The advantage of DCT-SE is that without loss of measurement precision it provides lower computational complexity to implement 3D reconstruction from nonlinearly distorted fringe patterns and, at the same time, survives the random noise. Simulations and experiments show that the proposed DCT-SE is a fast, accurate, and efficient reconstruction algorithm for digital projection-based fringe pattern profilometry techniques. c 2006 Optical Society of America OCIS codes: 120.6650, 120.2650, 150.6910.

This paper presents a new approach to fringe pattern profilometry. In this paper, a generalized model describing the relationship between the projected fringe pattern and the deformed fringe pattern is derived, in which the projected fringe pattern can be arbitrary rather than being limited to being sinusoidal, as are those for the conventional approaches. Based on this model, what is believed to be a new approach is proposed to reconstruct the three-dimensional object surface by estimating the shift between the projected and deformed fringe patterns. Additionally, theoretical analysis, computer simulation, and experimental results are presented, which show how the proposed approach can significantly improve the measurement accuracy, especially when the fringe patterns are distorted by unknown factors. OCIS codes: 120.6650, 120.2650, 150.6910.