Satellite platform jitter is a non-negligible factor that affects the image quality of optical cameras. Considering the limitations of traditional platform jitter detection methods that are based on attitude sensors and remote sensing images, this paper proposed a jitter detection method using sequence CMOS images captured by rolling shutter for high-resolution remote sensing satellite. Through the three main steps of dense matching, relative jitter error analysis, and absolute jitter error modeling using sequence CMOS images, the periodic jitter error on the imaging focal plane of the spaceborne camera was able to be measured accurately. The experiments using three datasets with different jitter frequencies simulated from real remote sensing data were conducted. The experimental results showed that the jitter detection method using sequence CMOS images proposed in this paper can accurately recover the frequency, amplitude, and initial phase information of satellite jitter at 100 Hz, 10 Hz, and 2 Hz. Additionally, the detection accuracy reached 0.02 pixels, which can provide a reliable data basis for remote sensing image jitter error compensation.

Remotely sensed images degraded by additive white Gaussian noise (AWGN) have low-level vision, resulting in a poor analysis of their contents. To reduce AWGN, two types of denoising strategies, sparse-coding-model-based and deep-neural-network-based (DNN), are commonly utilized, which have their respective merits and drawbacks. For example, the former pursue enjoyable performance with a high computational burden, while the latter have powerful capacity in completing a specified task efficiently, but this limits their application range. To combine their merits for improving performance efficiently, this paper proposes a model-driven deep denoising (MD${}^3$) scheme. To solve the MD${}^3$ model, we first decomposed it into several subproblems by the alternating direction method of multipliers (ADMM). Then, the denoising subproblems are replaced by different learnable denoisers, which are plugged into the unfolded MD${}^3$ model to efficiently produce a stable solution. Both quantitative and qualitative results validate that the proposed MD${}^3$ approach is effective and efficient, while it has a more powerful ability in generating enjoyable denoising performance and preserving rich textures than other advanced methods.

Deep convolution neural networks have proven their powerful ability in comparing many tasks of computer vision due to their strong data learning capacity. In this paper, we propose a novel end-to-end denoising network, termed Fourier embedded U-shaped network (FEUSNet). By analyzing the amplitude spectrum and phase spectrum of Fourier coefficients, we find that low-frequency features of an image are in the former while noise features are in the latter. To make full use of this characteristic, Fourier features are learned and are concatenated as a prior module that is embedded into a U-shaped network to reduce noise while preserving multi-scale fine details. In the experiments, we first present ablation studies on the Fourier coefficients’ learning networks and loss function. Then, we compare the proposed FEUSNet with the state-of-the-art denoising methods in quantization and qualification. The experimental results show that our FEUSNet performs well in noise suppression and preserves multi-scale enjoyable structures, even outperforming advanced denoising approaches.

Mixed (random and stripe) noise will cause serious degradation of optical remotely sensed image quality, making it hard to analyze their contents. In order to remove such noise, various inverse problems are usually constructed with different priors, which can be solved by either model-based optimization methods or discriminative learning methods. However, they have their own drawbacks, such as the former methods are flexible but are time-consuming for the pursuit of good performance; while the later methods are fast but are limited for extensive applications due to their specialized tasks. To fast obtain pleasing results with combination of their merits, in this paper, we propose a novel denoising strategy, namely, Dual Denoiser Driven Convolutional Neural Networks (D³CNNs), to remove both random and stripe noise. The D³CNNs includes the following two key parts: one is that two auxiliary variables respective for the denoised image and the stripe noise are introduced to reformulate the inverse problem as a constrained optimization problem, which can be iteratively solved by employing the alternating direction method of multipliers (ADMM). The other is that the U-shape network is used for the denoised auxiliary variable while the residual CNN (RCNN) for the stripe auxiliary variable. The subjectively and objectively comparable results of experiments on both synthetic and real-world remotely sensed images verify that the proposed method is effective and is even better than the state-of-the-arts.

In this article, we propose an effective grasp detection network based on an improved deformable convolution and spatial feature center mechanism (DCSFC-Grasp) to precisely grasp unidentified objects. DCSFC-Grasp includes three key procedures as follows. First, improved deformable convolution is introduced to adaptively adjust receptive fields for multiscale feature information extraction. Then, an efficient spatial feature center (SFC) layer is explored to capture the global remote dependencies through a lightweight multilayer perceptron (MLP) architecture. Furthermore, a learnable feature center (LFC) mechanism is reported to gather local regional features and preserve the local corner region. Finally, a lightweight CARAFE operator is developed to upsample the features. Experimental results show that DCSFC-Grasp achieves a high accuracy (99.3% and 96.1% for the Cornell and Jacquard grasp datasets, respectively) and even outperforms the existing state-of-the-art grasp detection models. The results of real-world experiments on the six-DoF Realman RM65 robotic arm further demonstrate that our DCSFC-Grasp is effective and robust for the grasping of unknown targets.

Recent advancements in network and multimedia technologies have facilitated the distribution and sharing of digital videos over the Internet. These long videos contain very complex contents. Additionally, it is very challenging to use as few frames as possible to cover the video contents without missing too much information. There are at least two ways to describe these complex videos contents with minimal frames: the keyframes extracted from the video or the video summary. The former lays stress on covering the whole video contents as much as possible. The latter emphasizes covering the video contents of interest. As a consequence, keyframes are widely used in many areas such as video segmentation and object tracking. In this paper, we propose a keyframe extraction method based on multiple features via a novel combinatorial optimization algorithm. The key frame extraction is modeled as a combinatorial optimization problem. A fast dynamic programming algorithm based on a forward non-overlapping transfer matrix in polynomial time and a 0-1 integer linear programming algorithm based on an overlapping matrix is proposed to solve our maximization problem. In order to quantitatively evaluate our approach, a long video dataset named 'Animal world' is self-constructed, and the segmentation evaluation criterions are introduced. A good result is achieved on 'Animal world' dataset and a public available Keyframe-Sydney KFSYD dataset ^[1].