Kianoush Nazarpour

Wenjuan Zhong, Chenfei Ma, Kianoush Nazarpour

Thumb gestures provide an effective and unobtrusive input modality for wearable and always-available human-machine interaction. Wrist-worn surface electromyography (sEMG) has emerged as a promising approach for compact and wearable human-machine interfaces. However, compared to forearm sEMG, the impact of electrode configuration on wrist-based decoding performance remains understudied. We systematically investigated electrode configuration strategies for wrist-based thumb-movement recognition using high-density (HD) and low-density (LD) sEMG measurement systems. We considered factors such as muscle region, reference scheme, channel count, and spatial density of the electrode. Experimental results show that 1) extensor-side electrodes outperform flexor-side electrodes (HD: 0.871 vs. 0.821; LD: 0.769 vs. 0.705); 2) monopolar recordings consistently outperform bipolar configurations (15 channel with HD monopolar vs. LD bipolar: 0.885 vs. 0.823); and 3) increasing channel count enhances performance, but exhibits diminishing returns. We further show that electrode spatial distribution introduces a trade-off between spatial coverage and compactness. The findings suggest that the effectiveness of wrist-worn sEMG systems depends less on the deployment of a large number of electrodes in a broad sensing area and more on the optimization of electrode placement and the referencing scheme. This work provides practical guidelines for developing efficient wrist-worn sEMG-based gesture recognition systems.

Rasool Ameri, Ali Alameer, Saideh Ferdowsi et al.

Dictionary learning is a cornerstone of image classification. We set out to address a longstanding challenge in using dictionary learning for classification; that is to simultaneously maximise the discriminability and sparse-representability power of the learned dictionaries. Upon this premise, we designed class-specific dictionaries incorporating three factors: discriminability, sparsity and classification error. We integrated these metrics into a unified cost function and adopted a new feature space, i.e., histogram of oriented gradients (HOG), to generate the dictionary atoms. The rationale of using HOG features for designing the dictionaries is their strength in describing fine details of crowded images. The results of applying the proposed method in the classification of Chinese handwritten numbers demonstrated enhanced classification performance $(\sim98\%)$ compared to state-of-the-art deep learning techniques (i.e., SqueezeNet, GoogLeNet and MobileNetV2), but with a fraction of parameters. Furthermore, combination of the HOG features with dictionary learning enhances the accuracy by $11\%$ compared to the case where only pixel domain data are used. These results were supported when the proposed method was applied to both Arabic and English handwritten number databases.

Ghazal Ghazaei, Federico Tombari, Nassir Navab et al.

Prosthetic hands can help people with limb difference to return to their life routines. Commercial prostheses, however have several limitations in providing an acceptable dexterity. We approach these limitations by augmenting the prosthetic hands with an off-the-shelf depth sensor to enable the prosthesis to see the object's depth, record a single view (2.5-D) snapshot, and estimate an appropriate grasp type; using a deep network architecture based on 3D point clouds called PointNet. The human can act as the supervisor throughout the procedure by accepting or refusing the suggested grasp type. We achieved the grasp classification accuracy of up to 88%. Contrary to the case of the RGB data, the depth data provides all the necessary object shape information, which is required for grasp recognition. The PointNet not only enables using 3-D data in practice, but it also prevents excessive computations. Augmentation of the prosthetic hands with such a semi-autonomous system can lead to better differentiation of grasp types, less burden on user, and better performance.

Ghazal Ghazaei, Iro Laina, Christian Rupprecht et al.

Humans excel in grasping and manipulating objects because of their life-long experience and knowledge about the 3D shape and weight distribution of objects. However, the lack of such intuition in robots makes robotic grasping an exceptionally challenging task. There are often several equally viable options of grasping an object. However, this ambiguity is not modeled in conventional systems that estimate a single, optimal grasp position. We propose to tackle this problem by simultaneously estimating multiple grasp poses from a single RGB image of the target object. Further, we reformulate the problem of robotic grasping by replacing conventional grasp rectangles with grasp belief maps, which hold more precise location information than a rectangle and account for the uncertainty inherent to the task. We augment a fully convolutional neural network with a multiple hypothesis prediction model that predicts a set of grasp hypotheses in under 60ms, which is critical for real-time robotic applications. The grasp detection accuracy reaches over 90% for unseen objects, outperforming the current state of the art on this task.