Multi-Scale Shape Adaptive Network for Raindrop Detection and Removal from a Single Image.

Removing raindrops from a single image is a challenging problem due to the complex changes in shape, scale, and transparency among raindrops. Previous explorations have mainly been limited in two ways. First, publicly available raindrop image datasets have limited capacity in terms of modeling raindrop characteristics (e.g., raindrop collision and fusion) in real-world scenes. Second, recent deraining methods tend to apply shape-invariant filters to cope with diverse rainy images and fail to remove raindrops that are especially varied in shape and scale. In this paper, we address these raindrop removal problems from two perspectives. First, we establish a large-scale dataset named RaindropCityscapes, which includes 11,583 pairs of raindrop and raindrop-free images, covering a wide variety of raindrops and background scenarios. Second, a two-branch Multi-scale Shape Adaptive Network (MSANet) is proposed to detect and remove diverse raindrops, effectively filtering the occluded raindrop regions and keeping the clean background well-preserved. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art raindrop removal methods. Moreover, the extension of our method towards the rainy image segmentation and detection tasks validates the practicality of the proposed method in outdoor applications.

An Adaptive Nonlocal Mean Filter for PolSAR Data with Shape-Adaptive Patches Matching.

The traditional nonlocal filters for polarimetric synthetic aperture radar (PolSAR) images are based on square patches matching to obtain homogeneous pixels in a large search window. However, it is still difficult for the regular patches to work well in the complex textured areas, even when the patch size has a small enough setting (e.g., 3 × 3 windows). Therefore, this paper proposes an adaptive nonlocal mean filter with shape-adaptive patches matching (ANLM) for PolSAR images. Mainly, the shape-adaptive (SA) matching patches are constructed by combining the polarimetric likelihood ratio test for coherency matrices (PolLRT-CM) and the region growing (RG), which is called PolLRT-CMRG. It is used to distinguish the homogeneous and heterogeneous pixels in textured areas effectively. Then, to enhance the filtering effect, it is necessary to take the adaptive threshold selection of similarity test (Simi-Test) into consideration. The simulated, low spatial resolution SAR580-Convair and high spatial resolution ESAR PolSAR image datasets are selected for experiments. We make a detailed quantitative and qualitative analysis for the filtered results. The experimental results have demonstrated that the proposed ANLM filter has better performance in speckle suppression and detail preservation than that of the traditional local and nonlocal filters.

Reticular Origami Soft Robotic Gripper for Shape-Adaptive and Bistable Rapid Grasping.

The top-down approach in designing and fabricating origami robots could achieve far more complicated functions with compliant and elegant designs than traditional robots. This study presents the design, fabrication, and testing of a reticular origami soft robotic gripper that could adapt to the shape of the grasping subject and grasp the subject within 80 ms from the trigger instance. A sensing mechanism consisting of the resistive pressure sensor array and flexible elongation sensor is designed to validate further the shape-adaptive grasping capability and model the rough shape and size of the subject. The grasping test on various objects with different shapes, surface textures, sizes, and living animals further validates the excellent grasping capabilities of the gripper. The gripper could be either actively triggered by actuation or passively triggered by a minimum of 0.0014 J disturbance energy. Such features make it particularly suitable for applications such as capturing underwater creatures and illegal drone control.

Bioinspired wet adhesive carboxymethyl cellulose-based hydrogel with rapid shape adaptability and antioxidant activity for diabetic wound repair.

Currently, adhesive hydrogels have shown promising effect in chronic diabetic wound repair. However, there are issues and challenges in treating diabetic wounds due to inadequate wet adhesion, unable to fill irregular and deep wounds, and oxidative stress. Herein, a mussel-inspired naturally hydrogel dressing with rapid shape adaptability, wet adhesion and antioxidant abilities for irregular, deep and frequently movement diabetic wounds repair was constructed by comprising catechol modified carboxymethyl cellulose (CMC-DA) and tannic acid. Benefiting from the reversible hydrogen bonding, the resulting hydrogels exhibited injectability, remarkable self-healing ability, rapid shape adaptability and strong tissue adhesion (45.9 kPa), thereby contributing to self-adaptive irregular-shaped wounds or moving joint parts. Especially, the adhesion strength of the hydrogel on wet tissue still remained at 14.9 kPa. Besides, the hydrogels could be easily detached from the skin by ice-cooling that avoided secondary damage caused by dressing change. Remarkably, the hydrogels possessed excellent antioxidant, satisfactory biocompatibility, efficient hemostasis and antibacterial properties. The in vivo evaluation further demonstrated that the hydrogel possessed considerable wound-healing promotion effect by regulating diabetic microenvironment, attributed to that the hydrogel could significantly reduce inflammatory response, alleviate oxidative stress and regulate neovascularization. Overall, this biosafe adhesive hydrogel had great potentials for diabetic wound management.

Vitrimeric shape memory polymer-based fingertips for adaptive grasping.

The variability in the shapes and sizes of objects presents a significant challenge for two-finger robotic grippers when it comes to manipulating them. Based on the chemistry of vitrimers (a new class of polymer materials that have dynamic covalent bonds, which allow them to reversibly change their mechanical properties under specific conditions), we present two designs as 3D-printed shape memory polymer-based shape-adaptive fingertips (SMP-SAF). The fingertips have two main properties needed for an effective grasping. First, the ability to adapt their shape to different objects. Second, exhibiting variable rigidity, to lock and retain this new shape without the need for any continuous external triggering system. Our two design strategies are: 1) A curved part, which is suitable for grasping delicate and fragile objects. In this mode and prior to gripping, the SMP-SAFs are straightened by the force of the parallel gripper and are adapted to the object by shape memory activation. 2) A straight part that takes on the form of the objects by contact force with them. This mode is better suited for gripping hard bodies and provides a more straightforward shape programming process. The SMP-SAFs can be programmed by heating them up above glass transition temperature (54°C) via Joule-effect of the integrated electrically conductive wire or by using a heat gun, followed by reshaping by the external forces (without human intervention), and subsequently fixing the new shape upon cooling. As the shape programming process is time-consuming, this technique suits adaptive sorting lines where the variety of objects is not changed from grasp to grasp, but from batch to batch.

Investigation on Surface Integrity of Nodular Cast Iron QT700-2 in Shape Adaptive Grinding.

Nodular cast iron QT700-2 is extensively used in automobile engine crankshaft parts due to its prime mechanical properties. The journal of a crankshaft is a curved surface, and traditional wheel grinding easily causes grinding burn and surface and subsurface damage. Shape adaptive grinding (SAG) is a flexible grinding technology, which has the advantages of low grinding force and temperature, and good grinding quality. It is suitable for machining curved surface parts with complex shapes. Therefore, the SAG surface integrity of nodular cast iron QT700-2 was experimentally investigated. The influence of grinding parameters on grinding force, material removal rate, grinding temperature, and surface integrity was studied, and the machining performance of SAG tools was evaluated. It was concluded that the grain size in SAG is the most important factor affecting the grinding force, material removal rate, and surface roughness; the influence of SAG grinding is very weak, mainly removing the workpiece material. Then, the influence law of SAG technology on the surface integrity of nodular cast iron QT700-2 was summarized, and the optimal grinding parameters were obtained, providing a reference for the curved surface grinding of nodular cast iron QT700-2 in the future.

Instantaneous self-healing and strongly adhesive self-adaptive hyaluronic acid-based hydrogel for controlled drug release to promote tendon wound healing.

The treatment of tendon injuries is an important healthcare challenge. Irregular wounds, hypocellularity, and prolonged inflammation impede the rate of healing for tendon injuries. To address these problems, a high-tenacity shape-adaptive, mussel-like hydrogel (PH/GMs@bFGF&PDA) was designed and constructed with polyvinyl alcohol (PVA) and hyaluronic acid grafted with phenylboronic acid (BA-HA) by encapsulating polydopamine and gelatin microspheres containing basic fibroblast growth factor (GMs@bFGF). The shape-adaptive PH/GMs@bFGF&PDA hydrogel can quickly adapt to irregular tendon wounds, and the strong adhesion (101.46 ± 10.88 kPa) can keep the hydrogel adhered to the wound at all times. In addition, the high tenacity and self-healing properties allow the hydrogel to move with the tendon without fracture. Additionally, even if fractured, it can quickly self-heal and continue to adhere to the tendon wound, while slowly releasing basic fibroblast growth factor during the inflammatory phase of the tendon repair process, promoting cell proliferation, migration and shortening the inflammatory phase. In acute tendon injury and chronic tendon injury models, PH/GMs@bFGF&PDA significantly alleviated inflammation and promoted collagen I secretion, enhancing wound healing through the synergistic effects of its shape-adaptive and high-adhesion properties.

Additively Manufactured Dual-Faced Structured Fabric for Shape-Adaptive Protection.

Fabric-based materials have demonstrated promise for high-performance wearable applications but are currently restricted by their deficient mechanical properties. Here, this work leverages the design freedom offered by additive manufacturing and a novel interlocking pattern to for the first time fabricate a dual-faced chain mail structure consisting of 3D re-entrant unit cells. The flexible structured fabric demonstrates high specific energy absorption and specific strength of up to 1530 J kg-1 and 5900 Nm kg-1 , respectively, together with an excellent recovery ratio of ≈80%, thereby overcoming the strength-recoverability trade-off. The designed dual-faced structured fabric compares favorably against a wide range of materials proposed for wearable applications, attributed to the synergetic strengthening of the energy-absorbing re-entrant unit cells and their unique topological interlocking. This work advocates the combined design of energy-absorbing unit cells and their interlocking to extend the application prospects of fabric-based materials to shape-adaptive protection.

Self-Cleaning and Shape-Adaptive Triboelectric Nanogenerator-Contained TiO2 Nanoparticle Coating.

With the rapid development of triboelectric nanogenerators (TENGs) for flexible wearable devices and electronic skins, challenges have gradually emerged related to the electrification surface, such as pollutant contamination and sophisticated surface adaptability. Hence, we report a simple spraying method to produce a shape-adaptive photocatalytic (SAP) triboelectric material with both self-cleaning and shape-adaptive functions. By spraying the polyvinyl alcohol solution with TiO2 photocatalysts and pre-drying cyclic, the SAP film can be adapted to a varied and intricate substrate. The highest transferred charge density of the SAP film reaches 197.5 µC/m2, when it contacts with the PTFE film. At the same time, it can degrade 74.4% of simulated pollutants under sunlight illumination, and 97% of the transferred charge density can be maintained after the degradation process, indicating good self-cleaning function and stable electrical output. Moreover, the spraying method of this allows it to have shape-adaptive functions. Accordingly, the SAP film can be deposited on the rectangular pyramid and hemispherical surface for fabricating TENGs with special shapes. This low-cost and simple spraying method further promotes the commercialized application of TENGs in the field of wearable devices and skin sensors.

Spatiotemporally dynamic therapy with shape-adaptive drug-gel for the improvement of tissue regeneration with ordered structure.

A spatiotemporally dynamic therapy (SDT) is proposed as a powerful therapeutic modality that provides spatially dynamic responses of drug-carriers for adapting to the wound microenvironment. Herein, dynamic chitosan-poly (ethylene glycol) (CP) Schiff-base linkages are employed to perform SDT by directly converting a liquid drug Kangfuxin (KFX) into a gel formation. The obtained KFX-CP drug-gel with shape-adaptive property is used to treat a representative oral mucositis (OM) model in a spatiotemporally dynamic manner. The KFX-CP drug-gel creates an instructive microenvironment to regulate signaling biomolecules and endogenous cells behavior, thereby promoting OM healing by the rule of dynamically adjusting shape to fit the irregular OM regions first, and then provides space for tissue regeneration, over KFX potion control and the general hydrogel group of CP hydrogel and KFX-F127. Most interestingly, the regenerated tissue has ordered structure like healthy tissue. Therefore, the SDT provides a new approach for the design of next generation of wound dressing and tissue engineering materials.

A Shape-Adaptive Gallic Acid Driven Multifunctional Adhesive Hydrogel Loaded with Scolopin2 for Wound Repair.

Wound healing is one of the major challenges in the biomedical fields. The conventional single drug treatment has unsatisfactory efficacy, and the drug delivery effectiveness is restricted by the short retention on the wound. Herein, we develop a multifunctional adhesive hydrogel that can realize robust adhesion, transdermal delivery, and combination therapy for wound healing. Multifunctional hydrogels (CS-GA-S) are mixed with chitosan-gallic acid (CS-GA), sodium periodate, and centipede peptide-scolopin2, which slowly releases scolopin2 in the layer of the dermis. The released scolopin2 induces the pro-angiogenesis of skin wounds and enables excellent antibacterial effects. Separately, GA as a natural reactive-oxygen-species-scavenger promotes antioxidation, and further enables excellent antibacterial effects and wet tissue adhesion due to a Schiff base and Michael addition reaction for accelerating wound healing. Once adhered to the wound, the precursor solution becomes both a physically and covalently cross-linked network hydrogel, which has potential advantages for wound healing with ease of use, external environment-isolating, and minimal tissue damage. The therapeutic effects of CS-GA-S on wound healing are demonstrated with the full thickness cutaneous wounds of a mouse model. The significant improvement of wound healing is achieved for mice treated with CS-GA-S. This preparation reduces wound system exposure, prolongs local drug residence time, and improves efficacy. Accordingly, with the incorporation of scolopin2 into the shape-adaptive CS-GA hydrogel, the composite hydrogel possesses multi-functions of mechanical adhesion, drug therapy, and skin wound healing. Overall, such an injectable or sprayable hydrogel plays an effective role in emergency wound treatment with the advantage of convenience and portability.

Cellulose fibers-reinforced self-expanding porous composite with multiple hemostatic efficacy and shape adaptability for uncontrollable massive hemorrhage treatment.

Uncontrollable hemorrhage leads to high mortality and thus effective bleeding control becomes increasingly important in the military field and civilian trauma arena. However, current hemostats not only present limitation when treating major bleeding, but also have various side effects. Here we report a self-expanding porous composites (CMCP) based on novel carboxymethyl cellulose (CMC) fibers and acetalized polyvinyl alcohol (PVA) for lethal hemorrhage control. The CMC fibers with uniform fibrous structure, high liquid absorption and procoagulant ability, are evenly interspersed inside the composite matrix. The obtained composites possess unique fiber-porous network, excellent absorption capacity, fast liquid-triggered self-expanding ability and robust fatigue resistance, and their physicochemical performance can be fine-tuned through varying the CMC content. In vitro tests show that the porous composite exhibits strong blood clotting ability, high adhesion to blood cells and protein, and the ability to activate platelet and the coagulation system. In vivo hemostatic evaluation further confirms that the CMCP presents high hemostatic efficacy and multiple hemostatic effects in swine femoral artery major hemorrhage model. Additionally, the CMCP will not fall off from the injury site, and is also easy to surgically remove from the wound cavity after the hemostasis. Importantly, results of CT tomography and 3D reconstruction indicate that CMCP can achieve shape adaptation to the surrounding tissues and the wound cavities with different depths and shapes, to accelerate hemostasis while protecting wound tissue and preventing infection.

Shape-Adaptive, Self-Healable Triboelectric Nanogenerator with Enhanced Performances by Soft Solid-Solid Contact Electrification.

The viable application of soft electronics/robotics relies on the development of power devices which are desired to be flexible, deformable, or even self-healable. We report here a shape-adaptive, self-healable triboelectric nanogenerator (SS-TENG) for harvesting biomechanical energies. The use of a viscoelastic polymer, normally known as Silly Putty, as the electrification material and as the matrix of a carbon-nanotube-filled composite (CNT-putty) electrode endows the SS-TENG the capability of adapting to arbitrary irregular surfaces and instantaneous healing from mechanical damage (almost completely recovered in 3 min without extra stimuli). Furthermore, the output performances of the SS-TENG have also been significantly improved because (i) the ideal soft contact is achieved at the solid-solid interfaces for more effective contact electrification and (ii) the introduced cation dopants make the putty even more tribo-negative than polytetrafluoroethylene. The SS-TENG can be adhered to any curvy surface, tailored, and reshaped into arbitrary configurations and utilized as a power supply for small electronics, suggesting promising applications in soft electronics/robotics in the future.

Bio-Inspired Shape-Adaptive Soft Robotic Grippers Augmented with Electroadhesion Functionality.

Soft robotic grippers (SRGs) have been extensively employed in robotic grasping and manipulation applications due to the fact that they are beneficial for pick-and-place of difficult-to-handle and delicate objects with various geometries and stiffness in a comfortable and safer way. This article presents a bio-inspired and shape-adaptive SRG augmented with electroadhesion (EA) functionality, FinEA, by a cost-effective combination of a Fin Ray structured two-fingered SRG with two soft-stretchable EA pads. The EA pads were manufactured by screen printing a layer of electrically conductive and elastomeric carbon black powder mixed with polydimethylsiloxane onto a dielectric substrate. The compliant Fin Ray fingers, composed of soft longitudinal beams and rigid cross beams, were structurally optimized by the finite element method using ABAQUS/CAE based on three key parameters: the open angle of the longitudinal beams, the spacing between the cross beams, and the incline angle of the cross beams. The soft beams were produced by a traditional soft lithography method, whereas the rigid cross beams were three-dimensionally printed. The resultant FinEA grippers were capable of lifting not only flat/thin materials without distorting them due to the employment of EA, but also concave and convex objects due to the passively shape-adaptive Fin Ray structure and the EA functionality. In addition, the proposed FinEA grippers were able to grasp delicate materials and objects whose diameters are larger than the overall gripper length. Furthermore, 65% more weight in shear were picked up by the FinEA gripper when 4 kV was applied compared with 0 V. The FinEA concept provides useful and alternative solution for controllable adhesion-based SRGs and may facilitate the inspiration and development of future SRGs with added functionality and enhanced versatility.

Grab and Heat: Highly Responsive and Shape Adaptive Soft Robotic Heaters for Effective Heating of Objects of Three-Dimensional Curvilinear Surfaces.

Soft actuators have received great research attention because of the recent rise of soft robotics. However, these actuators could perform only relatively simple deformations (such as bending, twisting, etc.) for manipulation, limiting their functionality. Here, we develop highly responsive and shape adaptive soft robotic heaters which not only can achieve large degree of deformation but also can grab and heat objects of three-dimensional (3D) curvilinear surfaces. With intentionally synthesized and selected materials for device fabrication, a U-shaped soft robotic heater exhibits a deformation angle of more than 860° and a curvature of 4.0 cm-1 at a very low voltage of 2 V, and its curvature can quickly reach 1.31 cm-1 within 6 s. Moreover, the device can also function as a stable heat source with temperature of 203 °C upon actuation, demonstrating a maximum energy efficiency of 7.44% as a heater. Importantly, the soft robotic heaters can deform to enclose 3D curvilinear surfaces with pressure to enable intimate contact for more effective heat transfer. The unique utility of the soft robotic heaters is illustrated through the heating of objects of various 3D shapes, showcasing their potential applications in soft robotics, advanced thermal therapy, food handling and processing, etc.

Compressive sensing image recovery using dictionary learning and shape-adaptive DCT thresholding.

Compressed sensing (CS) has shown to be a successful technique for image recovery. Designing an effective regularization term reflecting the image sparse prior information plays a critical role in this field. Dictionary learning (DL) strategy alleviates the drawback of fixed bases. But the structure information of the image is easy to be blurred in complex regions due to the absence of sparsity in dictionary learning. This paper proposes a novel joint dictionary learning and Shape-Adaptive DCT (SADCT) thresholding method. We first propose to exploit sparsity of image in shape-adaptive regions, which is beneficial to medical images of complex textures. In this framework, the local sparsity depicts the smoothness redundancies exploited by dictionary learning. Moreover, the sparsity is enhanced especially in detail areas by the newly introduced SADCT thresholding. The attenuated SADCT coefficients are used to reconstruct a local estimation of the signal within the adaptive-shape support. Image is represented sparser in SADCT transform domain and the details of the image information can be kept with a much larger probability. Based on split Bregman iterations, an efficient alternating minimization algorithm is developed to solve the proposed CS medical image recovery problem. The results of various experiments on MR images consistently demonstrate that the proposed algorithm efficiently recovers MR images and shows advantages over the current leading CS reconstruction approaches.

Shape adaptive, robust iris feature extraction from noisy iris images.

In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate.