Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully understand a visual scene. Towards a deeper visual understanding, the interactions between objects, especially humans and objects are essential. Most prior works have obtained this information with a bottom-up approach, where the objects are first detected and the interactions are predicted sequentially by pairing the objects. This is a major bottleneck in HOI detection inference time. To tackle this problem, we propose UnionDet, a one-stage meta-architecture for HOI detection powered by a novel union-level detector that eliminates this additional inference stage by directly capturing the region of interaction. Our one-stage detector for human-object interaction shows a significant reduction in interaction prediction time 4x~14x while outperforming state-of-the-art methods on two public datasets: V-COCO and HICO-DET.
Humans, this species expert in grasp detection, can grasp objects by taking into account hand-object positioning information. This work proposes a method to enable a robot manipulator to learn the same, grasping objects in the most optimal way according to how the gripper has approached the object. Built on deep learning, the proposed method consists of two main stages. In order to generalize the network on unseen objects, the proposed Approach-based Grasping Inference involves an element decomposition stage to split an object into its main parts, each with one or more annotated grasps for a particular approach of the gripper. Subsequently, a grasp detection network utilizes the decomposed elements by Mask R-CNN and the information on the approach of the gripper in order to detect the element the gripper has approached and the most optimal grasp. In order to train the networks, the study introduces a robotic grasping dataset collected in the Coppeliasim simulation environment. The dataset involves 10 different objects with annotated element decomposition masks and grasp rectangles. The proposed method acquires a 90% grasp success rate on seen objects and 78% on unseen objects in the Coppeliasim simulation environment. Lastly, simulation-to-reality domain adaptation is performed by applying transformations on the training set collected in simulation and augmenting the dataset, which results in a 70% physical grasp success performance using a Delta parallel robot and a 2 -fingered gripper.
Salient object detection (SOD) aims to identify the most attractive objects within an image. Depending on the type of data being detected, SOD can be categorized into various forms, including RGB, RGB-D (Depth), RGB-T (Thermal) and light field SOD. Previous researches have focused on saliency detection with individual data type. If the RGB-D SOD model is forced to detect RGB-T data it will perform poorly. We propose an innovative model framework that provides a unified solution for the salient object detection task of three types of data (RGB, RGB-D, and RGB-T). The three types of data can be handled in one model (all in one) with the same weight parameters. In this framework, the three types of data are concatenated in an ordered manner within a single input batch, and features are extracted using a transformer network. Based on this framework, we propose an efficient lightweight SOD model, namely AiOSOD, which can detect any RGB, RGB-D, and RGB-T data with high speed (780FPS for RGB data, 485FPS for RGB-D or RGB-T data). Notably, with only 6.25M parameters, AiOSOD achieves excellent performance on RGB, RGB-D, and RGB-T datasets.
Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed \emph{Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC)} which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, \emph{etc.}) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with $<$1M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly $2\times$ reduction of computational cost on ResNet18. Code available at \href{https://github.com/hellozhuo/pidinet}{https://github.com/hellozhuo/pidinet}.
Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we make the first attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which performs structural switching solely relied on single-modal and multi-modal inputs. UniSOD achieves consistent performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks.
Purpose: In this paper, we present a novel approach to the automatic evaluation of open surgery skills using depth cameras. This work is intended to show that depth cameras achieve similar results to RGB cameras, which is the common method in the automatic evaluation of open surgery skills. Moreover, depth cameras offer advantages such as robustness to lighting variations, camera positioning, simplified data compression, and enhanced privacy, making them a promising alternative to RGB cameras. Methods: Experts and novice surgeons completed two simulators of open suturing. We focused on hand and tool detection, and action segmentation in suturing procedures. YOLOv8 was used for tool detection in RGB and depth videos. Furthermore, UVAST and MSTCN++ were used for action segmentation. Our study includes the collection and annotation of a dataset recorded with Azure Kinect. Results: We demonstrated that using depth cameras in object detection and action segmentation achieves comparable results to RGB cameras. Furthermore, we analyzed 3D hand path length, revealing significant differences between experts and novice surgeons, emphasizing the potential of depth cameras in capturing surgical skills. We also investigated the influence of camera angles on measurement accuracy, highlighting the advantages of 3D cameras in providing a more accurate representation of hand movements. Conclusion: Our research contributes to advancing the field of surgical skill assessment by leveraging depth cameras for more reliable and privacy evaluations. The findings suggest that depth cameras can be valuable in assessing surgical skills and provide a foundation for future research in this area.
Honey bees pollinate about one-third of the world's food supply, but bee colonies have alarmingly declined by nearly 40% over the past decade due to several factors, including pesticides and pests. Traditional methods for monitoring beehives, such as human inspection, are subjective, disruptive, and time-consuming. To overcome these limitations, artificial intelligence has been used to assess beehive health. However, previous studies have lacked an end-to-end solution and primarily relied on data from a single source, either bee images or sounds. This study introduces a comprehensive system consisting of bee object detection and health evaluation. Additionally, it utilized a combination of visual and audio signals to analyze bee behaviors. An Attention-based Multimodal Neural Network (AMNN) was developed to adaptively focus on key features from each type of signal for accurate bee health assessment. The AMNN achieved an overall accuracy of 92.61%, surpassing eight existing single-signal Convolutional Neural Networks and Recurrent Neural Networks. It outperformed the best image-based model by 32.51% and the top sound-based model by 13.98% while maintaining efficient processing times. Furthermore, it improved prediction robustness, attaining an F1-score higher than 90% across all four evaluated health conditions. The study also shows that audio signals are more reliable than images for assessing bee health. By seamlessly integrating AMNN with image and sound data in a comprehensive bee health monitoring system, this approach provides a more efficient and non-invasive solution for the early detection of bee diseases and the preservation of bee colonies.
To autonomously navigate in real-world environments, special in search and rescue operations, Unmanned Aerial Vehicles (UAVs) necessitate comprehensive maps to ensure safety. However, the prevalent metric map often lacks semantic information crucial for holistic scene comprehension. In this paper, we proposed a system to construct a probabilistic metric map enriched with object information extracted from the environment from RGB-D images. Our approach combines a state-of-the-art YOLOv8-based object detection framework at the front end and a 2D SLAM method - CartoGrapher at the back end. To effectively track and position semantic object classes extracted from the front-end interface, we employ the innovative BoT-SORT methodology. A novel association method is introduced to extract the position of objects and then project it with the metric map. Unlike previous research, our approach takes into reliable navigating in the environment with various hollow bottom objects. The output of our system is a probabilistic map, which significantly enhances the map's representation by incorporating object-specific attributes, encompassing class distinctions, accurate positioning, and object heights. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively produce augmented semantic maps containing several objects (notably chairs and desks). Furthermore, our system is evaluated within an embedded computer - Jetson Xavier AGX unit to demonstrate the use case in real-world applications.
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space. However, most existing studies were conducted under a supervised setup which cannot scale well while handling various new data. Unsupervised domain adaptive BEV, which effective learning from various unlabelled target data, is far under-explored. In this work, we design DA-BEV, the first domain adaptive camera-only BEV framework that addresses domain adaptive BEV challenges by exploiting the complementary nature of image-view features and BEV features. DA-BEV introduces the idea of query into the domain adaptation framework to derive useful information from image-view and BEV features. It consists of two query-based designs, namely, query-based adversarial learning (QAL) and query-based self-training (QST), which exploits image-view features or BEV features to regularize the adaptation of the other. Extensive experiments show that DA-BEV achieves superior domain adaptive BEV perception performance consistently across multiple datasets and tasks such as 3D object detection and 3D scene segmentation.
Segmenting organs in CT scan images is a necessary process for multiple downstream medical image analysis tasks. Currently, manual CT scan segmentation by radiologists is prevalent, especially for organs like the pancreas, which requires a high level of domain expertise for reliable segmentation due to factors like small organ size, occlusion, and varying shapes. When resorting to automated pancreas segmentation, these factors translate to limited reliable labeled data to train effective segmentation models. Consequently, the performance of contemporary pancreas segmentation models is still not within acceptable ranges. To improve that, we propose M3BUNet, a fusion of MobileNet and U-Net neural networks, equipped with a novel Mean-Max (MM) attention that operates in two stages to gradually segment pancreas CT images from coarse to fine with mask guidance for object detection. This approach empowers the network to surpass segmentation performance achieved by similar network architectures and achieve results that are on par with complex state-of-the-art methods, all while maintaining a low parameter count. Additionally, we introduce external contour segmentation as a preprocessing step for the coarse stage to assist in the segmentation process through image standardization. For the fine segmentation stage, we found that applying a wavelet decomposition filter to create multi-input images enhances pancreas segmentation performance. We extensively evaluate our approach on the widely known NIH pancreas dataset and MSD pancreas dataset. Our approach demonstrates a considerable performance improvement, achieving an average Dice Similarity Coefficient (DSC) value of up to 89.53% and an Intersection Over Union (IOU) score of up to 81.16 for the NIH pancreas dataset, and 88.60% DSC and 79.90% IOU for the MSD Pancreas dataset.