Ruxandra Tapu

Dr. Ruxandra Tapu


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2016 in Sensors
Verified
Journal Article
Open access
PDF file
BMBogdan Mocanu
Bogdan Mocanu
RTRuxandra Tapu
Ruxandra Tapu
TZTitus Zaharia
Titus Zaharia
In the most recent report published by the World Health Organization concerning people with visual disabilities it is highlighted that by the year 2020, worldwide, the number of completely blind people will reach 75 million, while the number of visually impaired (VI) people will rise to 250 million. Within this context, the development of dedicated electronic travel aid (ETA) systems, able to increase the safe displacement of VI people in indoor/outdoor spaces, while providing additional cognition of the environment becomes of outmost importance. This paper introduces a novel wearable assistive device designed to facilitate the autonomous navigation of blind and VI people in highly dynamic urban scenes. The system exploits two independent sources of information: ultrasonic sensors and the video camera embedded in a regular smartphone. The underlying methodology exploits computer vision and machine learning techniques and makes it possible to identify accurately both static and highly dynamic objects existent in a scene, regardless on their location, size or shape. In addition, the proposed system is able to acquire information about the environment, semantically interpret it and alert users about possible dangerous situations through acoustic feedback. To determine the performance of the proposed methodology we have performed an extensive objective and subjective experimental evaluation with the help of 21 VI subjects from two blind associations. The users pointed out that our prototype is highly helpful in increasing the mobility, while being friendly and easy to learn.

28 October 2017 in Sensors
Verified
Journal Article
Open access
PDF file
RTRuxandra Tapu
Ruxandra Tapu
BMBogdan Mocanu
Bogdan Mocanu
TZTitus Zaharia
Titus Zaharia
In this paper, we introduce the so-called DEEP-SEE framework that jointly exploits computer vision algorithms and deep convolutional neural networks (CNNs) to detect, track and recognize in real time objects encountered during navigation in the outdoor environment. A first feature concerns an object detection technique designed to localize both static and dynamic objects without any a priori knowledge about their position, type or shape. The methodological core of the proposed approach relies on a novel object tracking method based on two convolutional neural networks trained offline. The key principle consists of alternating between tracking using motion information and predicting the object location in time based on visual similarity. The validation of the tracking technique is performed on standard benchmark VOT datasets, and shows that the proposed approach returns state-of-the-art results while minimizing the computational complexity. Then, the DEEP-SEE framework is integrated into a novel assistive device, designed to improve cognition of VI people and to increase their safety when navigating in crowded urban scenes. The validation of our assistive device is performed on a video dataset with 30 elements acquired with the help of VI users. The proposed system shows high accuracy (>90%) and robustness (>90%) scores regardless on the scene dynamics.

17 September 2018 in IEEE Access
Verified
Journal Article
Open access
BMBogdan Mocanu
Bogdan Mocanu
RTRuxandra Tapu
Ruxandra Tapu
TZTitus Zaharia
Titus Zaharia
In this paper, we introduce the DEEP-SEE FACE framework, an assistive device designed to improve cognition, interaction, and communication of visually impaired (VI) people in social encounters. The proposed approach jointly exploits computer vision algorithms (region proposal networks, ATLAS tracking and global, and low-level image descriptors) and deep convolutional neural networks in order to detect, track, and recognize, in real-time, various persons existent in the video streams. The major contribution of the paper concerns a global, fixed-size face representation that takes into the account of various video frames while remaining independent of the length of the image sequence. To this purpose, we introduce an effective weight adaptation scheme that is able to determine the relevance assigned to each face instance, depending on the frame degree of motion/camera blur, scale variation, and compression artifacts. Another relevant contribution involves a hard negative mining stage that helps us differentiating between known and unknown face identities. The experimental results, carried out on a large-scale data set, validate the proposed methodology with an average accuracy and recognition rates superior to 92%. When tested in real life, indoor/outdoor scenarios, the DEEP-SEE FACE prototype proves to be effective and easy to use, allowing the VI people to access visual information during social events.

21 May 2016 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
RTRuxandra Tapu
Ruxandra Tapu
BMBogdan Mocanu
Bogdan Mocanu
TZTitus Zaharia
Titus Zaharia

20 June 2021 in Sensors
Verified
Journal Article
Open access
PDF file
BMBogdan Mocanu
Bogdan Mocanu
RTRuxandra Tapu
Ruxandra Tapu
TZTitus Zaharia
Titus Zaharia
Emotion is a form of high-level paralinguistic information that is intrinsically conveyed by human speech. Automatic speech emotion recognition is an essential challenge for various applications; including mental disease diagnosis; audio surveillance; human behavior understanding; e-learning and human–machine/robot interaction. In this paper, we introduce a novel speech emotion recognition method, based on the Squeeze and Excitation ResNet (SE-ResNet) model and fed with spectrogram inputs. In order to overcome the limitations of the state-of-the-art techniques, which fail in providing a robust feature representation at the utterance level, the CNN architecture is extended with a trainable discriminative GhostVLAD clustering layer that aggregates the audio features into compact, single-utterance vector representation. In addition, an end-to-end neural embedding approach is introduced, based on an emotionally constrained triplet loss function. The loss function integrates the relations between the various emotional patterns and thus improves the latent space data representation. The proposed methodology achieves 83.35% and 64.92% global accuracy rates on the RAVDESS and CREMA-D publicly available datasets, respectively. When compared with the results provided by human observers, the gains in global accuracy scores are superior to 24%. Finally, the objective comparative evaluation with state-of-the-art techniques demonstrates accuracy gains of more than 3%.

1 July 2019 in IEEE Access
Verified
Journal Article
Open access
RTRuxandra Tapu
Ruxandra Tapu
BMBogdan Mocanu
Bogdan Mocanu
TZTitus Zaharia
Titus Zaharia
In this paper, we introduce the DEEP-HEAR framework, a multimodal dynamic subtitle positioning system designed to increase the accessibility of deaf and hearing impaired people (HIP) to multimedia documents. The proposed system exploits both computer vision algorithms and deep convolutional neural networks specifically designed and tuned in order to detect and recognize the identity of the active speaker. The main contributions of the paper concern: a novel method dedicated to recognizing various characters existent in the video stream. A video temporal segmentation algorithm that divides the video sequence into semantic units, based on face tracks and visual consistency. Finally, the core of our approach concerns a novel active speaker recognition method relying on the multimodal information fusion from the text, audio, and video streams. The experimental results carried out on a large scale dataset of more than 30 videos, validate the proposed methodology with average accuracy and recognition rates superior to 90%. Moreover, the method shows robustness to important object/camera motion and face pose variation, yielding gains of more than 8% in precision and recall rates when compared with state-of-the-art techniques. The subjective evaluation of the proposed dynamic subtitle positioning system demonstrates the effectiveness of our approach.