Classification of trampoline jumps using inertial sensors

Abstract

The automatic segmentation and classification of an unknown motion data stream according to given motion categories constitute an important research problem with applications in computer animation, medicine and sports sciences. In this paper, the scenario of trampoline motions is considered, where an athlete performs a routine consisting of sequence of jumps that belong to predefined motion categories such as pike jumps or somersaults. As main contribution, a fully automated approach for capturing, segmenting, and classifying trampoline routines according to these categories is introduced. Since trampoline motions are highly dynamic and spacious, optical motion capturing is problematic. Instead, it is reverted to a small number of inertial sensors attached to the athlete's body. To cope with measurement noise and performance differences, suitable feature and class representations are introduced that are robust to spatial and temporal variations while capturing the characteristics of each motion category. The experiments show that the approach reliably classifies trampoline jumps across different athletes even in the presence of significant style variations.

Validity of a Microsensor-Based Algorithm for Detecting Scrum Events in Rugby Union

“…The results of the scrum algorithm are in agreement with a recent systematic review that evaluated the use of microsensors for the detection of sport-specific movements. 11 This technology has been applied in cricket to count balls bowled 12 and bowling intensity, 28 baseball throwing, 13 tennis serves, 29 and several individual, 11,[30][31][32] snow, 11,[33][34][35][36][37][38] and water-based 11,[39][40][41] sports. Microsensors and associated algorithms have been used to detect tackles in rugby league 14 with accuracy improving with greater impact forces and longer duration of events.…”

Auditory Coding of Reaching Space

“…The sensors (size: 38 mm × 53 mm × 21 mm, weight: 30 g) were attached on the middle of the right shoulder, the right upper arm, the right lower arm, and the back of the right hand. The inertial sensors provided 3D acceleration data (up to eighteen times of the acceleration of gravity), 3D rate of turn (up to 1200 • /s), three degrees of freedom orientation and a sampling rate up to 100 Hz depending on the number of sensors used [52,53]. Data of the inertial sensors were recorded while the model was executing reaching actions with the digitizing pen towards one of nine different target positions on the tablet (see Figure 3).…”

Trends Supporting the In-Field Use of Wearable Inertial Sensors for Sport Performance Evaluation: A Systematic Review

“…For non-cyclic tasks, temporal parameters were identified to measure critical temporal events (blade–puck contact time in ice hockey [ 206 , 309 ], cricket bowling [ 227 ] and, more specifically, ball release [ 288 ]), or detect task phases and critical events (in ski jumping [ 90 , 91 ], half-pipe snowboard [ 159 ], bowling [ 180 ], baseball swing [ 146 , 179 ], instep kick [ 228 ], karate front kick [ 273 ], diving trampoline jumps [ 161 ], artistic gymnastics springboard jumps [ 187 ], golf [ 171 ], javelin throw [ 270 ], soccer turning manoeuvres [ 241 ], swimming tumble turn [ 192 , 197 , 285 ] and start [ 193 ] and cricket bowling [ 264 ]).…”

“…Body segment orientation was usually estimated by fusing data from different sensors, for example, using MIMU data alone to estimate trunk inclination during a sprint start [ 69 ], running on a track [ 295 ], during a golf swing [ 238 , 314 ], and during outdoor activities, such as snowboarding [ 333 ]. Inclination of body segments and angular velocity about the cranio–caudal axis were also estimated during trampoline jumps [ 161 ]. Pelvis orientation was dealt with in swimming [ 192 ] and climbing [ 279 ].…”